Interface for a virtual digital assistant

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 spoken user input via an input device;
• generating a first plurality of candidate interpretations of the received spoken user input;
• generating a second plurality of candidate interpretations, wherein the second plurality of candidate interpretations is a subset of the first plurality of candidate interpretations;
• deriving a representation of user intent based on the second plurality of candidate interpretations, wherein an association between the user intent and a respective candidate interpretation is added to context information;
• identifying, based on the user intent, at least one task;
• executing the at least one task;
• and
• providing an output based on the at least one executed task.

A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a first electronic device, the one or more programs including instructions for:

• receiving spoken user input via an input device;
• generating a first plurality of candidate interpretations of the received spoken user input;
• generating a second plurality of candidate interpretations, wherein the second plurality of candidate interpretations is a subset of the first plurality of candidate interpretations;
• deriving a representation of user intent based on the second plurality of candidate interpretations, wherein an association between the user intent and a respective candidate interpretation is added to context information;
• identifying, based on the user intent, at least one task;
• executing the at least one task;
• and
• providing an output based on the at least one executed task.

A computer-implemented method, comprising:

• at an electronic device with one or more processors and memory:
• receiving spoken user input via an input device;
• generating a first plurality of candidate interpretations of the received spoken user input;
• generating a second plurality of candidate interpretations, wherein the second plurality of candidate interpretations is a subset of the first plurality of candidate interpretations;
• deriving a representation of user intent based on the second plurality of candidate interpretations, wherein an association between the user intent and a respective candidate interpretation is added to context information;
• identifying, based on the user intent, at least one task;
• executing the at least one task;
• and
• providing an output based on the at least one executed task.