United Services Automobile Association (Usaa)

International Business Machines Corporation

Gregory B Yarbrough

Vijay Jayapalan

Eric J Smith

John McChesney TenEyck, Jr

Janelle Denice Dziuk

Emily Margaret Gray

David Patrick Dixon

Gregory David Hansen

Megan Sarah Jennings

Samip Dilip Mehra

Charles Balasingh

Bipin Chadha

Ryan Thomas Russell

Bryan J Osterkamp

Ruthie D Lyle

Ravi Durairaj

Joel S Hartshorn

Qunying Kou

William Daniel Farmer

Jeffrey David Calusinski

Madhusudhana Rao Abburi

Peter C Bahrs

Michael J Dockter

Jon Daniel McEachron

Jon D Mceachron

Enrique Vicente Kortright

Technology for determining a queue position of a call from a user can include receiving, at an enterprise, the call from a user device associated with the user. The user device includes an application associated with the enterprise. The call is placed into an on-hold queue. A weighted level of importance associated with the call is determined based on call history information associated with the user device and call frequency associated with the user. The weighted level of importance is compared to at least one weight threshold. A wait time for the call is decreased based on the weighted level of importance meeting or exceeding the at least one weight threshold.

Method and apparatus for determining an on-hold queue position of a call

The present embodiments relate to on demand generation of curated audio content. Responsive to initiation of an electronic communication by a client, audio relating to a client speaking to the operator can be processed to derive a series of insights relating to features of the audio. Previously recorded audio relating to the operator can be combined with a text-based script to generate audio content. The audio content can be modified using the series of derived insights. The modified audio content can include a series of disclaimers that are played back to the client. Generation of the modified audio content can be dynamically generated responsive to detecting a trigger that allows for on-demand generation of the modified audio content.

Recipient customized generative voice modeling

Various embodiments described herein relate to a call management system that aims to provide a more efficient, secure, and dynamic technique for authenticating a user based on a location of the user. A server of the call management system receives a phone call from a user device. The server transfers the phone call to an analyst device. When the analyst device accepts the phone call, the server starts an electronic communication session between the user device and the analyst device. The server then determines a current location of the user. The server further determines a question for authentication of the user based on the current location. The server transmits the question to the analyst device. The analyst device transmits the question to the user device via the server. In response to an answer received from the user device, the server authenticates the user.

Systems and methods for location based authentication

Implementations are disclosed to automatically evaluate, detect, or predict an event, and provide customized virtual assistance to a user based on the event. The implementations include a system capable of pulling data from a client device, detecting an event based on the pulled data, and pushing customized digital resources to the client device based on the detected event.

Systems and methods for automatic detection of an event and providing resources customized based on the event

Data analysis, filter, and presentation techniques are described for an example call management system. An example method for a data management system includes receiving, from a user device, an account identifier of a first person, receiving, from the user device, a first message related to a topic of conversation to be discussed during a telephone call with the first person, determining, based on the account identifier and within a pre-determined time period, a presence of a set of data that describes conversation(s) from prior telephone call(s)/chat(s) with the first person, and sending, to a computer, at least some data from the set of data and a second message that indicates that the telephone call is mapped to a second person, where the computer is configured to display on a screen the second message and a presentation option that presents the at least some data via the computer.

Data analysis, filter and presentation techniques for call management systems

Techniques are described for real time monitoring and tagging of media content generated during a service session between an individual and a service representative (SR). Media content received during a service session may be dynamically tagged with one or more metadata tags during the service session, the tag(s) indicating portion(s) of the media content that potentially include sensitive information. Tagging may be based on a SR's gestures, clicks, keystrokes, mouse-overs, and/or other actions performed in a SR user interface (UI) during the service session. The media content may be redacted based on the tags to remove and/or obfuscate potentially sensitive information.

Dynamic tagging of media for service sessions

Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Learning based metric determination and clustering for service routing

A system for measuring effectiveness of a customer service platform comprises a server configured to receive a first set of data related to an interaction between a first person and an automated communication channel, receive a second set of data related to a conversation between the first person and a second person on a call, determine, from the first set of data, a third set of word(s) that describe an intent of the first person to perform a task via the customer service platform, determine, from the second set of data, a fourth set of word(s) that describes an outcome accomplished during the call, calculate a value that describes a similarity between the third set of word(s) and the fourth set of word(s), and determine an effectiveness measure of the customer service platform based at least in part on a comparison of the value with a pre-determined threshold.

Interaction effectiveness measurements

Embodiments disclosed herein describe vehicle-based authentication protocols. An illustrative authentication server may receive a request to authenticate a user connected from a mobile device. The authentication server may transmit a request to the mobile device to transmit geolocation data of the mobile device. In response, the mobile device may transmit a stream of its geolocation data. Based upon the received geolocation data stream, the authentication server may determine that the mobile device in a motion and select a vehicle-based authentication protocol to request geolocation data of a trusted vehicle. The authentication server may compare the mobile device geolocation data stream and the vehicle geolocation data stream to determine a similarity score. If the similarity score is above a threshold, the authentications server may authenticate the user. In some cases, the authentication server may authenticate the user if the mobile device is connected to the trusted vehicle.

Systems and methods of multi-factor authentication utilizing a vehicle

Technology for placing a user on-hold can include sending a push notification to a user device after the call has been placed on-hold. A link in the push notification can request authentication credentials from the user. When the authentication credentials have been received and verified, a chat window can be launched via an application on the user device. The intent of the call can be determined based at least in part by information received via the chat window. The authentication information and the intent of the call can be transferred to a representative answering the call.

On-hold experience

A method for routing customer service requests to call centers includes collecting data associated with customer service experience between a customer and a call center regarding a completed customer call. The collected data is analyzed to determine a quality of customer service for one or more completed calls between the customer and the call center. A nature of an incoming customer call is determined. The incoming customer call is routed to a call center based upon making reference to the analyzed collected data such that the nature of the customer call matches with corresponding one or more favorable attributes of the call center.

Growing community of inventors

San Antonio, TX, United States of America

Gregory B Yarbrough