T-mobile Usa, Inc.

Verathon Inc.

Timothy Shelton

Jonathan Soini

Alex Thanh Nguyen

Kevin Lau

Ganesh Balgum

Tony Giannini

Vikas Verma

Gerald J McMorrow

Vikram Chalana

William Louis Barnard

Stephen Dudycha

Robert Stamm

Boua Lor

Jonathan Regalado

Brandon Shurick

Craig Medin

A text representation is received from a virtual assistant application on a user device. The text representation may be generated via a speech-to-text engine of the virtual assistant application from audio speech spoken by a customer. Device diagnostic data of the user device is also received from the virtual assistant application. An identifier of the customer is placed in an assistance queue. At least information in the text representation and the device diagnostic data is analyzed to determine an issue associated with the user device and a solution for resolving the issue, so that the solution is applied. In response to the identifier of the customer reaching a front of the assistance queue, session state information that includes at least the text representation and a description of the issue is provided to a support application. A voice support session is initiated between the support application and the virtual assistant application.

Device-based audio processing for enhanced customer support

Systems and methods are described herein for providing multiple, different types of information for mobile devices and associated users to requesting systems, such as customer service systems provided by telecommunications carriers. The systems and methods may generate a single API that, when called by a requesting system (e.g., via a request transmitted by the requesting system that includes subscriber or device information), provides data collected from multiple, disparate data sources back to the requesting system via the single API.

Single interface for provisioning collected data to requesting systems

The present disclosure describes techniques for monitoring telemetry data that relates to processing of client data on one or more data cluster(s) and dynamically re-routing client data to another data cluster for processing, based on an analysis of the telemetry data. Particularly, a Load Balancing and Data Prioritization (LB-DP) system is described that can monitor telemetry data associated with processing client data, and further generate a cluster-telemetry metric for each data cluster that quantifies whether a user experience on a client device is likely to be influenced by a data latency (I.e. delay) in processing client data. In some examples, the LB-DP System may prioritize processing some instances of client data over others, based on client profile data that prioritizes some clients over others. In other examples, the LB-DP system may selectively schedule a later time interval for processing of an instance of client data.

Data prioritization and scheduling system

Load balancing and data prioritization system

A remote support installation mechanism provides for the installation of a remote support client application onto a user device. A server may receive a request for a remote support eligibility status from a device agent application on a user device that is loaded with an installer package for a remote support client application. The remote support client application may be used to initiate a remote support session with a remote support application on a remote support server to provide a computing terminal with remote support access to the user device. The server may determine based on at least one of a device management database or a user account database that the user device qualifies for remote support. Accordingly, the server may send an install command to trigger an installation of the remote support client application on the user device from the installer package.

Remote support installation mechanism

System and method of intelligent application diagnostics of a user device (UD). Upon every first time period, the key performance indicators (KPI's) of the processes running on the UD are determined. The top predetermined number (N) of processes that are using the most computing resources are filtered and their KPI's are stored in a local memory. The KPI's of the remaining processes are discarded. This process is repeated at every first time period. At every second time period, the filtered KPI's of every iteration of the first time period are retrieved from the local memory and sent to a remote monitoring server for analysis and storage. The filtered metrics are removed from the local memory.

Intelligent application diagnostics

A workflow engine on a computing device is used to resolve a trouble ticket. Preliminary data is retrieved and one or more symptoms are received from a user device having a malfunction. The probability of each possible cause of the malfunction is determined. Upon determining that a probability of a mostly likely cause of the malfunction is above a predetermined threshold, a solution is provided. Upon determining that the probability of the most likely cause of the malfunction is not above the predetermined threshold, then entering a loop of performing diagnostic steps until the likely cause of the malfunction is above a predetermined threshold. Each diagnostic step is performed automatically, if the workflow engine determines that it can. If the diagnostic step cannot be performed automatically, the CSR is guided on how to accommodate the diagnostic step.

Diagnostic and workflow engine with system integration

A workflow engine may be used to resolve service issues in a more expedient and effective manner. The workflow engine may select a troubleshooting flow to detect problems associated with a user device that uses communication services provided by a wireless telecommunication network. The workflow engine may determine alert notifications that are relevant to the troubleshooting operations. The workflow engine may make such a determination based on information from multiple data sources of the wireless telecommunication network. The workflow engine may further assign priority ratings to the alert notifications. Subsequently, a presentation layout may be assigned to the troubleshooting operations of the troubleshooting flow and the alert notifications by the workflow engine based on the priority ratings. The troubleshooting operation and the alert notifications are then provided for presentation on a computing device according to the presentation layout by the workflow engine.

Workflow engine for troubleshooting user device issues

In some implementations, a computing device may download a campaign from a server. The campaign may include a trigger and one or more actions associated with the trigger. In response to detecting that the trigger occurred, the computing device may perform the one or more actions associated with the trigger. The trigger may comprise an event that occurs at the computing device or a short message service (SMS) message that originates from the server.

Triggering actions on a computing device

A system which includes at least one ultrasound data collection device which is programmable to carry out a specific ultrasound procedure on a selected part of a human body of a patient. The resulting ultrasound data is transmitted via a local server at the site of the data collection device to the internet and from there to a web database server which processes the raw ultrasound data to produce medical result information, including ultrasound images, which is then sent to a skilled technician, who accepts the results, rejects or edits them. Accepted medical results are transmitted back to the medical practitioner, while edited medical results are reprocessed, the results of which are transmitted to the medical practitioner.

Growing community of inventors

North Bend, WA, United States of America

Timothy Shelton