US 12,216,742 B2Granted

Generative artificial intelligence for generating predicted effects in response to a synthetic stimulus

AssigneeWells Fargo Bank, N.A.

InventorNaveen Gururaja Yeri

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems, apparatuses, methods, and computer program products are disclosed for generating a predicted effect for a target cluster in response to a synthetic stimulus. An example method includes receiving a synthetic behavior prediction request and generating a plurality of clusters, wherein each cluster is associated with a corresponding centroid position. The method further includes selecting the target cluster from the plurality of clusters and generating the predicted effect for the target cluster in response to the synthetic stimulus based on the centroid position corresponding to the target cluster. The method further includes providing a predicted effect notification.

Claims20

Dependent claims

A method for generating a predicted effect for a target cluster in response to a synthetic stimulus, the method comprising:

receiving, by communications hardware, a synthetic behavior prediction request, wherein the synthetic behavior prediction request comprises (i) an indication of the synthetic stimulus and (ii) a target feature set;
generating, by cluster generation circuitry, a plurality of clusters, wherein each cluster is associated with a corresponding centroid position;
selecting, by prediction generation circuitry based on the target feature set, the target cluster from the plurality of clusters, wherein (a) the target cluster comprises one or more users and (b) each of the one or more users is associated with a feature set;
generating, by the prediction generation circuitry and using a stimulus prediction machine learning model, an updated feature set for each of the one or more users in response to the synthetic stimulus;
generating, by the cluster generation circuitry and based on the updated feature set for each of the one or more users, an updated centroid position for the target cluster;
generating, by the prediction generation circuitry and based on the updated centroid position corresponding to the target cluster, the predicted effect for the target cluster;
and
providing, by the communications hardware, a predicted effect notification, wherein the predicted effect notification comprises the predicted effect for the target cluster.

5 more elements

An apparatus for generating a predicted effect for a target cluster in response to a synthetic stimulus, the apparatus comprising:

communications hardware configured to:
receive a synthetic behavior prediction request, wherein the synthetic behavior prediction request comprises (i) an indication of the synthetic stimulus and (ii) a target feature set;
cluster generation circuitry configured to:
generate a plurality of clusters, wherein each cluster is associated with a corresponding centroid position;
and
prediction generation circuitry configured to:
select, based on the target feature set, the target cluster from the plurality of clusters, wherein (a) the target cluster comprises one or more users and (b) each of the one or more users is associated with a feature set,
generate, using a stimulus prediction machine learning model, an updated feature set for each of the one or more users in response to the synthetic stimulus,
wherein the cluster generation circuitry is further configured to generate, based on the updated feature set for each of the one or more users, an updated centroid position for the target cluster,
wherein the prediction generation circuitry is further configured to generate, based on the updated centroid position corresponding to the target cluster, the predicted effect for the target cluster,
wherein the communications hardware is further configured to provide a predicted effect notification, wherein the predicted effect notification comprises the predicted effect for the target cluster.

8 more elements

A computer program product for generating a predicted effect for a target cluster in response to a synthetic stimulus, the computer program product comprising at least one non-transitory computer-readable storage medium storing software instructions that, when executed, cause an apparatus to:

receive a synthetic behavior prediction request, wherein the synthetic behavior prediction request comprises (i) an indication of the synthetic stimulus and (ii) a target feature set;
generate a plurality of clusters, wherein each cluster is associated with a corresponding centroid position;
select, based on the target feature set, the target cluster from the plurality of clusters, wherein (a) the target cluster comprises one or more users and (b) each of the one or more users is associated with a feature set;
generate, using a stimulus prediction machine learning model, an updated feature set for each of the one or more users in response to the synthetic stimulus:
generate, based on the updated feature set for each of the one or more users, an updated centroid position for the target cluster:
generate, based on the updated centroid position corresponding to the target cluster, the predicted effect for the target cluster;
and
provide a predicted effect notification, wherein the predicted effect notification comprises the predicted effect for the target cluster.

5 more elements

Dependencies are inferred from the claim text.