US 12,361,469 B1
Electronic service systems and methods
Will Kerns Maney, San Antonio, TX (US); Zachery C. Lake, Aubrey, TX (US); and Yevgeniy Viatcheslavovich Khmelev, San Antonio, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by United Services Automobile Association (USAA), San Antonio, TX (US)
Filed on Dec. 13, 2021, as Appl. No. 17/549,400.
Claims priority of provisional application 63/125,224, filed on Dec. 14, 2020.
Int. Cl. G06Q 30/00 (2023.01); G06F 9/54 (2006.01); G06F 16/9538 (2019.01); G06Q 20/12 (2012.01); G06Q 20/22 (2012.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0633 (2013.01) [G06F 9/541 (2013.01); G06F 16/9538 (2019.01); G06Q 20/12 (2013.01); G06Q 20/227 (2013.01)] 17 Claims
OG exemplary drawing
 
1. One or more tangible, non-transitory, computer-readable media, comprising instructions that, when executed by one or more processors, cause the one or more processors to:
receive, from an application programming interface (API), a list of objects corresponding to an online transaction;
retrieve a user profile from a user profile database, wherein the user profile is based on an identity of a user;
retrieve a classification lookup table based on the list of objects;
identify one or more potential classes of the list of objects using the user profile and the classification lookup table, wherein the one or more potential classes is specific to the user based on the user profile, wherein identifying the one or more potential classes comprises utilizing machine learning circuitry to:
receive transaction data and additional information about the user;
perform iterative optimization of an objective function based on training data, wherein the training data comprises the transaction data, and wherein the optimized objective function enables the machine learning circuitry to provide an output associated with new inputs not included in the training data; and
generate a prediction of the one or more potential classes for the list of objects;
provide, to the API, the one or more potential classes of each object for processing of the online transaction; and
cause generation and rendering of an interface representation at a user device, wherein the interface representation displays the list of objects, wherein the interface representation comprises an icon disposed adjacent to each object in the list of objects, and wherein an indication of a preferred payment method is dynamically overlaid onto the icon based on the identification of the one or more potential classes of each object in the list of objects.