| CPC G10L 15/1815 (2013.01) [B60K 35/00 (2013.01); G06F 3/167 (2013.01); G06F 9/54 (2013.01); G06F 16/3329 (2019.01); G06F 16/3344 (2019.01); G06F 16/9537 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01); G10L 13/02 (2013.01); G10L 13/08 (2013.01); G10L 15/183 (2013.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 15/30 (2013.01); G10L 21/06 (2013.01); H04M 1/6091 (2013.01); H04M 1/7243 (2021.01); H04M 1/72448 (2021.01); H04M 1/72484 (2021.01); G10L 13/00 (2013.01); G10L 15/1822 (2013.01)] | 33 Claims |

|
1. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving a first speech input from a user;
providing, based on the first speech input, an output to the user in a user session;
during the user session:
detecting at least one user interaction; and
in accordance with a determination that the at least one user interaction satisfies a minimum threshold interaction criteria, invoking a short-term memory component, the short-term memory component including information corresponding to device sensor data;
receiving a second speech input from the user;
obtaining, based on the information corresponding to the device sensor data, a representation of user intent corresponding to the second speech input, wherein the representation of user intent corresponding to the second speech input is obtained based on an interpretation of a previously received user input during the user session; and
performing a task based on the representation of user intent.
|