Truist Bank

Paul Gerard Mistor

Sudeshna Banerjee

Raphael Fitzgerald

Kevin Green

A system for identifying life events for individuals based on relationships found in data. The system includes a database containing data records and fields and identifying individuals involved in each record. A supplemental source of data including location and social media data is also included. The database and the supplemental source of data are provided to a computer which executes a machine learning algorithm configured to identify life events for the individuals based on clusters in the data, where the machine learning algorithm provides output data identifying the life events, and rating values for each of the life events for each of the individuals. A communication system algorithm sends actionable communications to particular ones of the individuals based on the output data. Unsupervised learning may be used for initial system training, and supervised learning for ongoing training.

Machine learning algorithm for predicting events using multiple disparate inputs

A system for monitoring quantized signals in a bidirectional data stream and alerting a networked device of metric divergence by georegion includes a computing system that automatically, for each of multiple user entities, receives input signals and stores corresponding records , associated with the user entity, each representing a quantized input event. The computing system increments a resource of the user entity by a respective input quantity. Georegion-specific attributes associated with a respective georegion are discriminated, and the input records are associated with georegion. The computing system measures user-specific georegion-specific metrics for each georegion and determines whether the metrics diverge from a georegion-specific index. An alert is sent across a network for display on a user device upon determining a user-specific georegion-specific metric diverges from a georegion-specific index.

Alerting networked devices of signal divergence by georegion

A system for improving distributed network data flow efficiency by using a machine learning model to engage a reduced set of unknown objects is disclosed. The system includes at least one processor, a communication interface communicatively coupled to the at least one processor, and a memory device storing executable code that, when executed causes the at least one processor to receive interaction data corresponding to interactions between known objects and unknown objects, develop an interaction map, develop a profile for each unknown object, process each unknown object using a machine learning algorithm to generate a reduced set of unknown objects most likely to reciprocate and identify properties of each unknown object, and trigger a communication to each of the reduced set of unknown objects.

Engaging unknowns in response to interactions with knowns

A monitoring system for detecting anomalous discharges stores input and output records, and fetches and discharges corresponding quantities to and from user resources. The output event records are discriminated for category attributes, and user-specific output category-specific metrics are aggregated for comparison to peer-representative output-category indexes. An alert is sent across a network connection for display on a user device upon determining the user-specific output category-specific metric diverges from the peer-representative output-category index. An alert, in some examples, indicates that the user-specific output category metric exceeds the peer-representative output-category index. Exposure of user-entity resources to outputs that are divergent from peer-representative levels is mitigated. The alert is advantageous to user entities and user devices, enabling early action to be taken by the user entity.

Time-based input and output monitoring and analysis to predict future inputs and outputs

An artificial intelligence (AI) system for guiding a user interaction in a phone call or chat session. The system includes a computer running an AI algorithm, such as a machine learning algorithm, which is trained to recognize patterns in user interaction dialog which lead to satisfactory outcomes for the user. The system may operate in a completely autonomous mode, or the system connect a human agent in the loop. The algorithm adaptively guides the dialog to achieve a favorable outcome based on the current status of the dialog—including identifying a next question to ask, information to provide, or an action to take. The algorithm is trained via supervised learning using real dialog transcriptions from past user interactions which have been supplemented with decision points and outcomes. After deployment, update training may be performed on the algorithm using data captured by the system after the user interactions.

User interaction artificial intelligence chat engine for integration of automated machine generated responses

A system for monitoring quantized signals in a bidirectional data stream and alerting a networked device of metric divergence by georegion includes a computing system that automatically, for each of multiple user entities, receives input signals and stores corresponding records, associated with the user entity, each representing a quantized input event. The computing system increments a resource of the user entity by a respective input quantity. Georegion-specific attributes associated with a respective georegion are discriminated, and the input records are associated with georegion. The computing system measures user-specific georegion-specific metrics for each georegion and determines whether the metrics diverge from a georegion-specific index. An alert is sent across a network for display on a user device upon determining a user-specific georegion-specific metric diverges from a georegion-specific index.

Growing community of inventors

Winston-Salem, NC, United States of America

Paul Gerard Mistor