Truist Bank

Kenneth William Cluff

Peter Councill

James Xu

Qing Li

Harold Thomas Wood, Iii

Dontá Lamar Wilson

Jane Moury Kane

Glenn Thomas Nofsinger

David Wright

Adam Thomas Lewis

David Pham

Kevin Green

Brian Franklin Kramer

Rinku Saha

A system and method for training an artificial intelligence engine for real-time monitoring to eliminate false positives is disclosed. The system includes at least one processor, a communication interface coupled to the processor, and a memory device storing executable code. Executing the executable code causes the processor to receive data from an AI security model, receive data from a false positive database, and correlate both sets of data. The correlated data is used to generate a training dataset and a test dataset used to train a false positive identification model. After evaluating the false positive identification model, an AI engine is applied to user registration. The AI engine includes an AI security model and the false positive identification model. Additionally, a system for evaluating the security of user registration utilizing the false positive identification model is disclosed.

Training an artificial intelligence engine for real-time monitoring to eliminate false positives

A system for training a model from a subset of data representing decentrally stored source databases. A key variable repository module operably couples the databases and includes an AI program with a scanner algorithm and a profiler algorithm. The scanner algorithm receives the training data from a source interface, compresses the training data, and synchronizes the training data with the meta-data using a meta-database interface. The profiler algorithm receives the meta-data from the meta-database interface, generates granular data types for the meta-data, determines training variables indicative of the meta-data, generates variable probability distributions, produces training variable associations, and modifies the meta-database to include the probability distributions and associations using the meta-data interface. The key interface allows for searching the meta-database for training variables, variable probability distributions, and/or variable associations. A model of the system may be trained in less time with a subset of data associated with the training variable.

Accelerated model training from disparate and heterogeneous sources using a meta-database

A computing system is configured to generate a predictive model during training of a machine learning program using a training data set including a personal data set of a plurality of first users. The predictive model is configured to generate predicted survey data with respect to a second user by correlating a personal data set of the second user to the personal data set of at least one of the first users. The predicted survey data includes data regarding the predicted responses of the second user to a survey from which the survey data of each first user is derived, as well as one or more assessment scores calculated from the survey. The computing system is configured to take an action with respect to a user device of the second user in reaction to the generating of the predicted survey data regarding the second user.

Training machine learning model based on user actions and responses

A computing system is configured to generate a predictive model during training of a machine learning program using a training data set including a personal data set of a plurality of first users. The predictive model is configured to predict a first predicted assessment score at a first instance and a second predicted assessment score at a second instance with respect to a second user. The computing system determines whether the first predicted assessment score is different from the second predicted assessment score, and whether a first data entry of the personal data set of the second user changed between the first instance and the second instance. The computing system takes or recommends an action corresponding to a reversal in the change in the first data entry in order to alter the predicted assessment score of the second user.

Automatically adjusting system activities based on trained machine learning model

A computing system is configured to generate a predictive model during training of a machine learning program using a training data set including a personal data set of a plurality of first users. The predictive model is configured to generate a predicted assessment score with respect to a second user by correlating a personal data set of the second user to the personal data set of at least one of the first users, with the generating of the predicted assessment score occurring automatically when a data entry of the personal data set of the second user is determined to have changed by the computing system. The computing system is configured to report the automatically generated predicted assessment score to the second user via a user device of the second user.

Using machine learning model to automatically predict updated assessment score

Disclosed are systems and methods that automatically classify, segment, and parse content data using artificial intelligence and natural language processing technology, and generate graphical user interfaces that allow end users to dynamically filter content data for display. The systems processes volumes of content data to identify interrogative data, content sources that generated the interrogative data, and subject identifiers relating to the content data. The system generates graphical user interfaces that allow end users to effectively filter the data by choosing between layouts that display one or more of the various categories of data, including the interrogative data, content source identifiers, and/or subject identifiers. The user interfaces include content view input functions that utilizes mapping data to locate and extract segments of the underlying content data from which displayed data is derived, thereby allowing end users to expediently review both the aggregated and reduced content data and the underlying source data.

Automated processing and dynamic filtering of content for display

A system for maintaining a meta-database including meta-data representing decentralized data from source databases, which cause inefficient selection of modeling data and/or variables. Each of source and meta-data interfaces communicate with the respective database(s). A key variable repository module operably couples the databases and includes an AI program with a scanner algorithm and a profiler algorithm. The scanner algorithm receives the source data from the source interface, compresses the data, and synchronizes the data with the meta-data using the meta-database interface. The profiler algorithm receives the meta-data from the meta-database interface, generates granular data types for the meta-data, determines variables indicative of the meta-data, generates variable probability distributions, produces variable associations, and modifies the meta-database to include the probability distributions and associations using the meta-data interface. The key interface allows for searching the meta-database for variables, variable probability distributions, and/or variable associations to more efficiency select modeling data and/or variables.

Construction of a meta-database from autonomously scanned disparate and heterogeneous sources

A system and method is described for labelling data for trigger identification. The system and method comprising receiving data, transforming the data, extracting content from the data, processing data content through a classification machine learning model to receive a label, and trigger a secondary system based on the label. The system and method may further include maintaining a database of labeled data.

System and method for labelling data for trigger identification

Disclosed are systems and methods that automatically classify, filter, and reduce large volumes of feedback data as a function of time using artificial intelligence technology. The aggregated feedback data is reduced by representing the feedback data as sets of descriptors corresponding to one or more time periods that are displayed on a graphical user interface. Feedback data packets are parsed by labeling the feedback data packets with a time period identifier. The feedback data packets are processed utilizing neural network technology to classify the feedback data according to one or more subject identifiers that are each associated with a subject vector. A descriptor analysis is used to process the subject vectors and the feedback data packets to generate descriptor sets comprising one or more descriptors as well as weighting data for each descriptor.

Graphical user interface for display of real-time feedback data changes

A system for interfacing with a meta-database representing data from a plurality of source databases. A key variable repository module operably couples the databases and includes an AI program with a scanner algorithm and a profiler algorithm. The scanner algorithm receives the source data from a source interface, compresses the data, and synchronizes the data with the meta-data using a meta-database interface. The profiler algorithm receives the meta-data from the meta-database interface, generates granular data types for the meta-data, determines variables indicative of the meta-data, generates variable probability distributions, produces variable associations, and modifies the meta-database to include the probability distributions and associations using the meta-data interface. A graphical user interface allows for generating a representation of a location of data associated with a user identified variable with the source databases, the probability distribution for the user identified variable, or any associations for the user identified variable.

Graphical user interface enabling interactive visualizations using a meta-database constructed from autonomously scanned disparate and heterogeneous sources

Growing community of inventors

Powhatan, VA, United States of America

Kenneth William Cluff