US 2025/0094786 A1Published application

Generative artificial intelligence (ai) training and ai-assisted decisioning

AssigneeState Farm Mutual Automobile Insurance Company

InventorsAaron Williams, Kenneth D. Sanders

Life of this patent

Estimating the term…

Loading patent…

Abstract

A computer system is configured to store historical data identifying a plurality of events and corresponding outcomes, train an artificial intelligence (AI) model using the historical data generate a trained AI model, and generate a user interface enabling access to functionality of the trained AI model at a remote computing device. The computer system is also configured to receive, via the user interface, an operational request including initial input data, identify additional data missing from the operational request, retrieve, in response to a plurality of queries and responses through the user interface, the additional data, and execute the trained AI model using the initial input data and the additional data, wherein a model output from the trained AI model includes an operational response. The computer system is further configured to automatically initiate the operational response, including transmitting a notification and executing one or more functions responsive to the operational request.

Claims20

Dependent claims

A computer system comprising at least one processor in communication with at least one memory device, the at least one processor programmed to:

store historical data in the at least one memory device, the historical data identifying a plurality of events, corresponding aspects associated with the events, and corresponding outcomes associated with the events;
train an artificial intelligence (AI) model using the historical data as a training set to generate a trained AI model that, when executed using unmodelled input data, is configured to output one or more predicted outcomes associated with the input data;
generate a user interface enabling access to functionality of the trained AI model at one or more remote computing devices;
receive, via the user interface executed at a first remote computing device, an operational request including initial input data associated with a subject event;
identify additional data missing from the operational request;
retrieve, in response to a plurality of queries and responses through the user interface, the additional data;
execute the trained AI model using the initial input data and the additional data, wherein a model output from the trained AI model includes an operational response to the operational request associated with the subject event;
and
automatically initiate the operational response, including transmitting a notification of the operational response via the user interface and executing one or more functions responsive to the operational request using at least one of the initial input, the additional data, and the model output.

6 more elements

A computer-implemented method for training and executing an artificial intelligence (AI) model, the method implemented using an access management server computing device including at least one processor and at least one memory, the method comprising:

storing historical data in the at least one memory device, the historical data identifying a plurality of events, corresponding aspects associated with the events, and corresponding outcomes associated with the events;
training an AI model using the historical data as a training set to generate a trained AI model that, when executed using unmodelled input data, is configured to output one or more predicted outcomes associated with the input data;
generating a user interface enabling access to functionality of the trained AI model at one or more remote computing devices;
receiving, via the user interface executed at a first remote computing device, an operational request including initial input data associated with a subject event;
identifying additional data missing from the operational request;
retrieving, in response to a plurality of queries and responses through the user interface, the additional data;
executing the trained AI model using the initial input data and the additional data, wherein a model output from the trained AI model includes an operational response to the operational request associated with the subject event;
and
automatically initiating the operational response, including transmitting a notification of the operational response via the user interface and executing one or more functions responsive to the operational request using at least one of the initial input, the additional data, and the model output.

6 more elements

Dependencies are inferred from the claim text.