US 12,476,924 B2
Systems and methods for ranking access configurations
Dominic Joseph Cannizzaro, McLean, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Sep. 6, 2023, as Appl. No. 18/462,042.
Prior Publication US 2025/0080476 A1, Mar. 6, 2025
Int. Cl. H04L 47/80 (2022.01); H04L 47/70 (2022.01)
CPC H04L 47/808 (2013.01) [H04L 47/822 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system for ranking access configurations for requested resources, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable media storing instructions that, when executed by the one or more processors, cause operations comprising:
receiving, from a user via a user terminal, a resource access request comprising a user identifier and a resource identifier for a requested resource, wherein the requested resource is a processing resource of a computing system;
based on the user identifier, obtaining a resource access history for the user, the resource access history comprising a plurality of previous resource access requests from the user, by:
comparing the user identifier with a plurality of user identifiers in a user database, wherein the user database comprises a list of user identifiers and corresponding resource access histories;
based on determining that the user identifier matches a corresponding user identifier of the plurality of user identifiers, extracting a plurality of resource access events and a corresponding plurality of timestamps; and
storing the plurality of resource access events as the resource access history for the user;
based on the resource access history, determining a measure of risk associated with allocating resources to the user, wherein the measure of risk indicates a computational cost associated with providing the requested resource;
based on the resource identifier for the requested resource and the measure of risk, generating a plurality of access configurations available to the user for obtaining access to the requested resource, wherein the plurality of access configurations indicate options for accessing the requested resource;
processing the resource access history and the plurality of access configurations using a machine learning model to generate a plurality of probabilities, wherein each probability of the plurality of probabilities indicates a likelihood of the user accessing the requested resource using a corresponding access configuration of the plurality of access configurations;
based on comparing each probability of the plurality of probabilities with a threshold probability, determining a subset of access configurations having a corresponding probability that is greater than the threshold probability;
based on a plurality of parameters corresponding to each access configuration of the subset of access configurations, generating an access benefit metric for each access configuration of the subset of access configurations, wherein each access benefit metric indicates a measure of resource savings for the system when the user accesses the requested resource through an associated access configuration;
generating, for display on a user interface associated with the user terminal, a ranked representation of the subset of access configurations displayed in order of decreasing access benefit metric for the associated access configuration;
receiving, via the user terminal from the user, a user response comprising a chosen access configuration from the subset of access configurations; and
providing access to the requested resource for the user according to parameters associated with the chosen access configuration.