Capital One Services, LLC

Kevin M Lowe

Tania Cruz Morales

Julian Duque

Luis Catacora

Helen Temesghen-Blount

Systems and methods for generating real-time location-based notifications are described. In some aspects, the system receives a recurring user activity that is recurring at a previous location during a recurring time period. Based on detecting that a current location of the user is in proximity of the previous location during an instance of the recurring time period, the system determines whether any user activity was executed while the user is present at the current location. Based on determining that a current user activity was executed by the user different from the recurring user activity, the system determines whether the current user activity is a substitute for an instance of the recurring user activity. The system updates a measure of elasticity of the recurring user activity based on determining that the current user activity is a substitute for the instance of the recurring user activity.

Systems and methods for generating real-time location-based notifications

Methods and systems use an additional determination to generate predictions of future data processing load predictions. Specifically, the methods and systems generate additional predictions based on other data sets and data calculation methodologies (e.g., data with non-homogeneous time dependencies). The methods and systems then use these additional predictions to determine whether or not the prediction of the real-time average of data processing loads is an outlier. Thus, the methods and systems generate a time-specific data processing prediction.

Systems and methods for correlating probability models with non-homogenous time dependencies to generate time-specific data processing predictions

In some implementations, a system may receive exchange data that includes a credential for an exchange and an indication of an entity associated with the exchange. The system may determine that an entity location is within a threshold distance of a target location included in a set of target locations. The system may determine a baseline location associated with a user. The system may determine that the baseline location is outside of a threshold proximity of all target locations included in the set of target locations. The system may transmit, to a mobile device associated with the user, a message that includes an indication of the target location based on determining that the entity location is within the threshold distance of the target location and based on determining that the baseline location is outside of the threshold proximity of all target locations included in the set of target locations.

Location-based messaging

In some implementations, a voice assistance device may receive an indication of a visualization change associated with the virtual or augmented reality environment. The voice assistance device may determine that a change value, calculated based on the indication of the visualization change, satisfies a relevance threshold. The voice assistance device may apply, based on the indicator of change satisfying the relevance threshold, a description model to determine at least one sentence describing the virtual or augmented reality environment. The voice assistance device may apply a text-to-speech model to the at least one sentence to generate a digital sound signal and may transmit, to an output component, the digital sound signal.

Voice assistance in virtual reality environments and augmented reality environments

Systems as described herein generate an outstanding check alert. An alert generating server may receive transaction records associated with a plurality of checking accounts. The alert generating server may user a first machine learning classifier to determine a transaction pattern indicating a merchant has failed to process outstanding checks for a period of time. The alert generating server may receive sequential check information comprising at least one missing check number associated with a particular checking account. The alert generating server may user a second machine learning classifier to determine at least one outstanding check associated with the particular checking account. The alert generating server may send an alert indicating the at least one outstanding check to a user device.

Growing community of inventors

Richmond, VA, United States of America

Kevin M Lowe