The Toronto-Dominion Bank
Systems and methods of generating responses associated with natural language input

Last updated:

Abstract:

Systems and methods of generating responses associated with natural language input. A system includes a communication module, a processor, and a memory. The memory stores instructions that, when executed, configure the processor to: transmit, to a conversation agent server, a natural language input and receive, from the conversation agent server, an intent and at least one parameter. The processor generates, based on the intent and the at least one parameter, a fulfillment query requesting access to personal data for generating a response to the natural language input, where the personal data is stored on a fulfillment server. The processor transmits the fulfillment query and receives a response indication from the fulfillment server. The processor generates a request for subsequent input, generates an updated conversation context based on the response indication and the intent, and transmits to the conversation agent server, the updated conversation context.

Status:
Grant
Type:

Utility

Filling date:

18 Dec 2020

Issue date:

19 Jul 2022