Apparatuses, systems, methods, and computer program products for legacy-based automated customer assistance
AssigneeWells Fargo Bank, N.A.
InventorsNaga Jyothi Avusingi, Shanmukeswara Rao Donkada, Gopinath Dhanapal
Life of this patent
Estimating the term…
Abstract
An apparatus, system, method, and computer program product are provided for improved automated customer assistance based on legacy data, which may be associated with an ancestor in a family that owns a family business. Some example embodiments use legacy data not associated with the client but associated with the client's predecessor. Some example embodiments employ machine-learning modeling to facilitate automated customer assistance to generate advisories to clients that to assist the client in addressing the implementation of strategies or specific events.
Claims23
An apparatus for providing automated customer assistance comprising a processor and a memory, the memory comprising instructions that configure the apparatus to:
- receive, over a network, by communications circuitry, one or more legacy data objects associated with an ancestor, wherein the one or more legacy data objects use a first data format;
- convert, by the processor, legacy data in the one or more legacy data objects to a second data format;
- determine one or more legacy attributes associated with the one or more legacy data objects;
- generate one or more machine learning training sets based on the one or more legacy attributes;
- train one or more machine learning models with a first machine learning training set of the one or more machine learning training sets;
- generate, by a first machine learning model of the one or more machine learning models, —a first rule set based on one or more historical actions in the one or more legacy attributes, wherein the first rule set comprises one or more strategic actions, and wherein the first rule set is configured to be adjustable by a user device;
- receive, from the user device over the network, a business strategy indication and a historical evaluation indication associated with the ancestor;
- receive one or more client data objects associated with a client, wherein the one or more client data objects use the second data format;
- determine one or more suggestions based on the first rule set, the one or more client data objects, the business strategy indication, and the historical evaluation indication;
- and
- generate an advisory based on the one or more suggestions.
(canceled)
A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions configured to:
- receive, over a network, by communications circuitry, one or more legacy data objects associated with an ancestor, wherein the one or more legacy data objects use a first data format;
- convert legacy data in the one or more legacy data objects to a second data format;
- determine one or more legacy attributes associated with the one or more legacy data objects;
- generate one or more machine learning training sets based on the one or more legacy attributes;
- train one or more machine learning models with a first machine learning training set of the one or more machine learning training sets;
- generate, by a first machine learning model of the one or more machine learning models, a first rule set based on one or more historical actions in the one or more legacy attributes, wherein the first rule set comprises one or more strategic actions, and wherein the first rule set is configured to be adjustable by a user device;
- receive, from the user device over the network, a business strategy indication and a historical evaluation indication associated with the ancestor;
- receive one or more client data objects associated with a client, wherein the one or more client data objects use the second data format;
- determine one or more suggestions based on the first rule set, the one or more client data objects, the business strategy indication, and the historical evaluation indication;
- and
- generate an advisory based on the one or more suggestions.
(canceled)
14-20. (canceled)
A computer-implemented method for providing automated customer assistance, the computer-implemented method comprising:
- receiving, over a network, by communications circuitry, one or more legacy data objects associated with an ancestor, wherein the one or more legacy data objects use a first data format;
- converting, by a processor, legacy data in the one or more legacy data objects to a second data format;
- determining one or more legacy attributes associated with the one or more legacy data objects;
- generating one or more machine learning training sets based on the one or more legacy attributes;
- training one or more machine learning models with a first machine learning training set the one or more machine learning training sets;
- generating, by a first machine learning model of the one or more machine learning models, a first rule set based on one or more historical actions in the one or more legacy attributes, wherein the first rule set comprises one or more strategic actions, and wherein the first rule set is configured to be adjustable by a user device;
- receiving, from the user device over the network, a business strategy indication and a historical evaluation indication associated with the ancestor;
- receiving one or more client data objects associated with a client, wherein the one or more client data objects use the second data format;
- determining one or more suggestions based on the first rule set, the one or more client data objects, the business strategy indication, and the historical evaluation indication;
- and
- generating an advisory based on the one or more suggestions.
Dependencies are inferred from the claim text.