CPC G06F 16/2358 (2019.01) [G06F 16/24573 (2019.01); G06F 16/2471 (2019.01); G06F 16/248 (2019.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01)] | 18 Claims |
1. A method, comprising:
receiving, by a query management system of a virtual assistant, an access notification from a data source, the access notification being indicative of a request by the data source to be utilized with the virtual assistant;
analyzing, by the query management system, the data source to determine a query parameter associated with the data source;
training, by the query management system, a machine learning model based on historical data to determine a reliability score of a data source, the historical data being associated with using one or more other data sources to provide a response to a query associated with the query parameter and the reliability score being indicative of an ability of the data source to respond to the query associated with the query parameter;
determining, by the query management system utilizing the trained machine learning model, a reliability score for the query parameter associated with the data source based on at least one of:
source data of the data source, and
other source data associated with the one or more other data sources;
configuring, by the query management system and based on the reliability score satisfying a reliability threshold, a communication interface with the data source; and
integrating, by the query management system, the data source for use with the virtual assistant in accordance with the reliability score, the query parameter, and the communication interface.
|