20250232016. Machine-learning Re (Wells Fargo Bank, N.A.)
MACHINE-LEARNING FOR REAL-TIME AND SECURE ANALYSIS OF DIGITAL METRICS
Abstract: disclosed are example methods, systems, and devices that allow for executing machine-learning models for real-time and secure analysis of digital metrics. the techniques include generating metrics for identity elements stored in digital profiles of users. a subset of profiles can be identified that have metrics that fall below a predetermined thresholds, with which a training dataset can be generated. machine-learning models can be executed over the training dataset to train an artificial intelligence agent that receives digital profiles as input and outputs translational elements corresponding to identity elements in the digital profiles. after training, additional profiles can be input to the machine-learning models of the artificial intelligence agent to identify a second subset of digital profiles with corresponding metrics. electronic messages corresponding to the second subset can be generated and transmitted to one or more computing devices identified in the second subset of digital profiles.
Inventor(s): Thomas E. Bell, Peter Bordow, Julio Jiron, Akhlaq M. Khan, Volkmar Scharf-Katz, Jeff J. Stapleton, Richard Orlando Toohey, Ramesh Yarlagadda
CPC Classification: G06F21/316 ({by observing the pattern of computer usage, e.g. typical user behaviour})
Search for rejections for patent application number 20250232016
- Patent Applications
- Wells Fargo Bank, N.A.
- CPC G06F21/316
- Thomas E. Bell of San Francisco CA US
- Peter Bordow of Fountain Hills AZ US
- Julio Jiron of San Bruno CA US
- Akhlaq M. Khan of San Francisco CA US
- Volkmar Scharf-Katz of San Francisco CA US
- Jeff J. Stapleton of Arlington TX US
- Richard Orlando Toohey of San Francisco CA US
- Ramesh Yarlagadda of San Francisco CA US