公开(公告)号：US20250139371A1

公开(公告)日：2025-05-01

申请号：US18385229

申请日：2023-10-30

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani ,  Durgesh Kumar

IPC: G06F40/30 ,  G06N3/045

Abstract: An illustrative intent classification engine may access a text transcript and determine one or more features associated with the text transcript. Based on the one or more features, the intent classification engine may generate an aggregate embedding vector and provide the aggregate embedding vector as an input to a trained model configured to output an intent classification. Corresponding methods and systems are also disclosed.

公开(公告)号：US20230027936A1

公开(公告)日：2023-01-26

申请号：US17383631

申请日：2021-07-23

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani

IPC: G06F40/226 ,  G06F40/35 ,  G06F40/289 ,  G06F40/232 ,  G06N20/20

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, a conversation path associated with a revised code segment of a conversational interaction entity is identified by a processor. The conversation path has a predetermined intent. A conversational phrase is generated by the processor for the conversation path. The conversational interaction entity is employed by the processor using the conversation path and the conversational phrase to generate a resultant intent. An issue report is generated by the processor for the conversational interaction entity responsive to the resultant intent not matching the predetermined intent.

公开(公告)号：US20240096075A1

公开(公告)日：2024-03-21

申请号：US17933902

申请日：2022-09-21

Applicant: Verizon Patent and Licensing Inc.

Inventor： Subham Biswas ,  Saurabh Tahiliani

IPC: G06V10/82 ,  G06V10/70 ,  G06V10/776 ,  G06V10/778

CPC classification number: G06V10/82 ,  G06V10/768 ,  G06V10/776 ,  G06V10/7796

Abstract: A method may include receiving a number of images to train a first neural network, masking a portion of each of the images and inputting the masked images to the first neural network. The method may also include generating, by the first neural network, probable pixel values for pixels located in the masked portion of each of the plurality of images, forwarding the images including the probable pixel values to a second neural network and determining, by the second neural network, whether each of the probable pixel values is contextually suitable. The method may further include identifying pixels in each of the plurality of images that are not contextually suitable.

公开(公告)号：US20230403559A1

公开(公告)日：2023-12-14

申请号：US17838328

申请日：2022-06-13

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani

IPC: H04W12/106 ,  H04W4/14 ,  H04W12/088 ,  G06N3/08

CPC classification number: H04W12/106 ,  H04W4/14 ,  H04W12/088 ,  G06N3/08

Abstract: In an example, a text message sent by a first user equipment (UE) and addressed to a second UE is received. In response to receiving the text message, a set of information associated with the text message is determined based upon information determined by a first carrier of the first UE and/or the second UE. The text message is classified as spam or not spam based upon the set of information.

公开(公告)号：US12094181B2

公开(公告)日：2024-09-17

申请号：US17724036

申请日：2022-04-19

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani

IPC: G06V10/20 ,  G06N3/045 ,  G06V10/25 ,  G06V10/774 ,  G06V10/82 ,  G06V20/70

CPC classification number: G06V10/255 ,  G06N3/045 ,  G06V10/25 ,  G06V10/7747 ,  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：US11934614B1

公开(公告)日：2024-03-19

申请号：US17971145

申请日：2022-10-21

Applicant: VERIZON PATENT AND LICENSING INC.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani

IPC: G06F3/041 ,  G06F3/044 ,  H04N25/68

CPC classification number: G06F3/0418 ,  G06F3/0416 ,  G06F3/044 ,  G06F3/0412 ,  G06F3/0445 ,  H04N25/68

Abstract: Disclosed are systems and methods for an anomaly detection framework that operates as an executable analysis tool for devices to operate in order to determine whether the device contains an unresponsive touch screen (e.g., defective or malfunctioning touch screen). The disclosed framework can analyze the capacitance capabilities of the touch screen, inclusive of the touch layers associated with the touch screen panel, and determine when a device's touch screen is unresponsive to user provided input, which can be any type of touch or gesture provided on a touch screen.

公开(公告)号：US20230171644A1

公开(公告)日：2023-06-01

申请号：US17536971

申请日：2021-11-29

Applicant: Verizon Patent and Licensing Inc.

Inventor： Seng Gan ,  Subham Biswas ,  Christopher A. Graffeo ,  Saurabh Tahiliani

IPC: H04W28/08

CPC classification number: H04W28/0958

Abstract: A system described herein may provide a technique for the assignment of Centralized Units (“CUs”) to Distributed Units (“DUs”) in a radio access network (“RAN”) that includes a distributed or hierarchical arrangement of network infrastructure equipment. Different groups of DUs may be modeled based on usage or traffic patterns, and complementary groups of DUs may be identified based on measures of usage that may vary with time. For example, one model associated with one group of DUs may experience relatively heavy usage during morning hours and light usage during evening hours, and another model associated with a complementary group of DUs may experience relatively light usage during morning hours and heavy usage during evening hours.

公开(公告)号：US20250021818A1

公开(公告)日：2025-01-16

申请号：US18352437

申请日：2023-07-14

Applicant: Verizon Patent and Licensing Inc.

Inventor： Subham Biswas ,  Saurabh Tahiliani

IPC: G06N3/082 ,  G06N3/0495

Abstract: The present teaching relates to compressing a model for an application to generate a compressed model. The model has multiple layers, each of which has multiple nodes. Operating the model utilizing an application-dependent dataset, redundant nodes/layers in the model are identified via a loss-based assessment. The loss-based assessment using aggregated output vectors computed based on output vectors produced by the nodes/layers of the model in response to the data samples of the application-dependent dataset. Removing the redundant nodes/layers yields the compressed model.

公开(公告)号：US12197860B2

公开(公告)日：2025-01-14

申请号：US17383631

申请日：2021-07-23

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash Ranganathan ,  Saurabh Tahiliani

IPC: G06F40/226 ,  G06F40/35 ,  G06F40/56 ,  G06N20/20

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, a conversation path associated with a revised code segment of a conversational interaction entity is identified by a processor. The conversation path has a predetermined intent. A conversational phrase is generated by the processor for the conversation path. The conversational interaction entity is employed by the processor using the conversation path and the conversational phrase to generate a resultant intent. An issue report is generated by the processor for the conversational interaction entity responsive to the resultant intent not matching the predetermined intent.

公开(公告)号：US20240386887A1

公开(公告)日：2024-11-21

申请号：US18319729

申请日：2023-05-18

Applicant: Verizon Patent and Licensing Inc.

Inventor： Durgesh Kumar ,  Saurabh Tahiliani

IPC: G10L15/22 ,  G10L13/02 ,  G10L15/02 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183 ,  G10L25/63

Abstract: The present teaching relates to personalized IVR communications with a customer at a geo-locale. A first set of transcripts of the current and historic communications involving the customer and a second set of transcripts of historic communications associated with the geo-locale are analyzed to compute a personalized contextual vector, a geo-localized contextual vector, and a current text vector. The computed vectors are used by a language model to generate a personalized and geo-locale aware prompt, which is used to generate an IVR communication and is sent to the customer as a response.