| CPC G10L 15/22 (2013.01) [G06F 3/167 (2013.01); G10L 2015/221 (2013.01); G10L 2015/223 (2013.01)] | 16 Claims |
|
1. A method, the method comprising:
receiving, at a digital assistant on an information handling device, a command from a user, wherein the command comprises a high confidence portion and a low confidence portion;
determining, at the digital assistant and utilizing a machine-learning model, that at least a part of an output corresponding to the command can be performed by the digital assistant based upon the high confidence portion, wherein the determining comprises identifying an electronic efficiency of starting an action present within the at least a part of the output corresponding to the command is designated between one of: an efficiency mode of operation and a strict command mode of operation, wherein the identifying the electronic efficiency of starting the action is designated based upon an attribute of at least one of: the user and the device, wherein identifying the attribute comprises utilizing historical data identifying correlations between the high confidence portion of the command and an end action corresponding to the command; and
performing, using the digital assistant and responsive to determining the at least a part of the output of the command can be performed by the digital assistant, the at least a part of the output of the command associated with the high confidence portion, wherein the performing comprises performing the action based upon the electronic efficiency of the starting of the action of the command and the historical data used to identify the correlations between the high confidence portion of the command the end action corresponding to the command.
|