Verizon Patent and Licensing Inc.

Cellco Partnership

Sankar Shanmugam

Moorthy Sengottaiyan

Shahid Ahmed

Michelle Felt

Petri Virkkula

Sivagnanalingam Sivaganesh

Venkat Gaddam

Sm Masudur Rahman

Saivivek Thiyagarajan

Madhu Talupur

Srinivasa Kaniganti

Ying Sun

Sudhin Vellooparambil Latheef

Pradeep Bharthur Shanthraj

Neil Thomas Razzano

Venkateswara Rao Gaddam

Gayathri Chandrasekaran

Zulfiqer Sekender

Amit Mahajan

Arindam Mitra

Manmeet Kaur

Stephen John Soltys

Trisha Mahajan

RajeshKhanna Singa Ramalingam

Brian Matthew White

Tarun Verma

Denise Nicole Lyn-Shue

Amar Nageswaram

David J Strumwasser

Nagaraju Manchiraju

Nitin Ahuja

Thomas Michael McGurl

Shankar Arumugavelu

Rashmi Naik

Shoma Chakravarty

S M Masudur Rahman

John Van-Ryzin

Siva Sivaganesh

Seng Kin Liew

Thomas A Warren

Amol Chakradeo

Praveen K Muthu

Charles A Laney

Sathiyamoorthy Dhanapal

Elaine M Escher

Shan Olachery

Muhammad Salman Ali

Hannah Youngsil Moon

Rachel YuYin Ward

Arulvadivel Venugopal

Graham David Sysko

Alan Lobo

Samantha Kalita

Thiru Voonna

Sreeharsha Lanka

John Edwin Straley

Hilary Basch

Rosa Tavares

Alexander Papadopolo

Suja John

Shankar Venkatesan

Swapnil Mahankal

Zhidong Lu

Tiffany Chan

Peter Kyagaba Kisuule

Zhen Qin

William Cory Hawkins

Maheswaran Krishnan

Kumaradevan Chandrabose

Deenaraj Joshi Jangam

Joe Varghese

Ahmed Pasha Mohammed

Jangam Deenaraj Joshi

Sandeep Kumar

Daniel M Rivera

Matthew Farley Reeves

Lapfan Lam

Amit Kumar Shukla

Nash Sivaganesh

Kedar Kotkunde

Parthiv C Patel

Sridhar Sundaraju

Ravi Kotyala

In some implementations, an agent-assistance platform may receive a first call stream. The agent-assistance platform may identify a first topic of the first call stream. The agent-assistance platform may output, using a recommendation model, one or more recommendations associated with the first topic of the first call stream. The agent-assistance platform may determine whether a recommendation, of the one or more recommendations, is selected for inclusion in the first call stream. The agent-assistance platform may update the recommendation model with information indicating whether the recommendation is selected for inclusion in the first call stream. The agent-assistance platform may receive a second call stream. The agent-assistance platform may identify a second topic of the second call stream, the first topic being the same as the second topic. The agent-assistance platform may selectively output, using the updated recommendation model, the recommendation for the second call stream.

Systems and methods for adaptive computer-assistance prompts

In some implementations, a support system may receive, from a user device, a support request to setup a support session. The support system may establish the support session based on the support request by enabling support communications associated with the support session to be exchanged between a terminal device associated with the support system and the user device. The support system may determine an intent associated with the support session by using artificial intelligence processing to process one or more utterances received from the user device. The support system may provide, to the terminal device, a delegation message that includes an option to enable the support communications associated with the support session to be exchanged between the user device and an assisting device associated with the support system. The assisting device may execute an automated support agent. The support system may provide one or more support messages generated by the automated support agent to the user device based on a selection of the option included in the delegation message.

Systems and methods for an enhanced support session using an artificial intelligence-based conversational assistant

A device may receive real time audio data associated with a call between an agent and a customer, and may receive customer data identifying historical interactions with the customer. The device may receive chat data associated with the customer or interactive voice response (IVR) data associated with the customer, and may generate, based on the real time audio data, transcript data identifying a real time transcript of the call with the customer. The device may process the real time audio data, the customer data, the chat data or the IVR data, and the transcript data, with a machine learning model, to determine a customer intent and one or more actions to perform based on the customer intent; and may perform the one or more actions.

Systems and methods for utilizing a machine learning model to determine an intent of a voice customer in real time

A method, device, and computer-readable medium provide for receiving, via a chatbot access channel, a chat message from a user device associated with a customer chat session; determining that the chat message includes a customer intent that corresponds to a chat flow for the customer chat session; generating one or more suggested response messages based on the chat message, wherein at least one of the one or more suggested response messages includes a previously stored chat message response corresponding to the customer intent and approved by a service agent; presenting, via a display, a transcript of a messaging sequence for the customer chat session concurrently with a user interface that enables the service agent to perform an action with respect to the one or more suggested response messages; and sending, via the chatbot access channel, a selected one of the one or more suggested response messages to the user device.

Systems and methods for customer service agent-guided chat session digital assistant

A system described herein may provide for the adaptation and/or expansion of a natural language processing ('NLP') platform, that supports only a limited quantity of intents, such that the described system may support an unlimited (or nearly unlimited) quantity of intents. For example, a hierarchical structure of agents may be used, where each agent includes multiple intents. A top-level (e.g., master) agent may handle initial user interactions, and may indicate a next-level agent to handle subsequent interactions.

Systems and methods for dynamically expanding natural language processing agent capacity

A device receives provides content to a client device via a dual-panel user interface that includes a first panel and a second panel. The device receives, from the client device, information indicating a user interaction, and processes the information, with a first model, to determine a question based on the user interaction. The device utilizes natural language processing with the question to determine an intent of the question, and processes the intent of the question, with a second model, to map the intent of the question to a content answer to the question. The device adds additional user information, associated with a user of the client device, to the content answer to generate a personalized content response, and updates the first panel with the personalized content response to generate an updated first panel. The device provides the updated first panel, via the dual-panel user interface, to the client device.

Systems and methods for utilizing machine learning and natural language processing to provide a dual-panel user interface

A system is disclosed for chatbot conversation construction, and includes user interface, coupled to a conversation construction and management platform, configured to provide entry of intents, associated responses and search terms, and to construct and store conversation controllers, each based at least in part on one or more of the intents, and build conversation flows, each based at least in part on one or more of the conversation controllers. An artificial intelligence (AI) connector platform couples to the conversation construction and management platform, and is configured to receive natural language (NL) search data from a chatbot channel, format the NL search data into an input protocol of a selectable NL processing engine and receive a response from the NLP engine and, based at least in part on one or more of the conversation flows, convert the NLP engine response to a personalized response, and send the personalized response to the chatbot channel.

System and method for chatbot conversation construction and management

A device can be configured to provide a request for assistance with performing a task, receive instructions, launch, using the instructions, an application associated with the task, and cause display of a transparent overlay on top of a display of the application. The transparent overlay can include an instruction for a user, and the device can receive user input that corresponds to the instruction and perform an action based on the user input and the received instructions.

Method and device for a guided application to enhance a user interface

A device may receive an indication to establish a communication session between a first device and a second device for a file transfer. The device may receive, from the second device, metadata. The metadata may be used to identify files of a set of files. The device may identify the files for transfer from the second device to the first device based on the metadata. The device may cause multiple communication sessions to be established between the first device and the second device. The multiple connections may be used to transfer the files from the second device to the first device. The device may receive, from the second device, the files. The files may be received via the multiple communication sessions.

Increasing an efficiency of a file transfer by using multiple communication resources

A device may obtain data regarding application activity from a group of user devices. The application activity may relate to an application associated with network operator services provided by a network operator. The device may process the data regarding the application activity to generate a visualization of the application. The visualization of the application activity may include multiple tiers. The multiple tiers may correspond to at least a group of users, a user, and a session. The visualization may identify one or more errors associated with the application activity. The device may provide the visualization of the application activity for display. The visualization may be provided for display via a client device associated with the network operator. The device may automatically implement, without human intervention, a correction to the one or more errors.

System and methods for application activity capture, error identification, and error correction

Systems and methods for managing user interface elements using gestures are disclosed. In some implementations, a block representing a plurality of user interface elements is displayed on a touch screen of a device. A first gesture is initiated at a position corresponding to the block representing the plurality of the user interface elements is received via the touch screen. A first path corresponding to the first gesture is stored in a memory. At least a portion of the plurality of user interface elements are displayed on the touch screen in positions along the first path.

Managing user interface elements using gestures

Techniques described herein may allow for the registration of demo devices (e.g., for-sale wireless telephones, tablet computers, etc.), and the presentation of content, such as promotional content, for the demo devices. The demo devices may output a beacon via a short-range protocol, which may include unique identifiers of the demo devices. When a customer device approaches a demo device, the customer device may automatically detect the beacon and obtain promotional content regarding the demo device, and present the promotional content to a customer.

Smart content delivery using beacons

Growing community of inventors

Dayton, NJ, United States of America

Sankar Shanmugam