Maintaining context information between user interactions with a voice assistant
Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A first task is performed using a first parameter. A text string is obtained from a speech input received from a user. Based at least partially on the text string, a second task different from the first task or a second parameter different from the first parameter is identified. The first task is performed using the second parameter or the second task is performed using the first parameter.
1. A method for operating an automated assistant, comprising:
at an electronic device comprising a processor and memory storing instructions for execution by the processor:
performing a first task using a first parameter;
providing a first response to a user based on a result of performing the first task using the first parameter;
in a first operation:
obtaining a first text string from a first speech input received from the user;
determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and
in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter:
performing the second task using the first parameter; and
providing a second response to the user based on a result of performing the second task using the first parameter; and
in a second operation:
obtaining a second text string from a second speech input received from the user;
determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;
in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task:
performing the first task using the second parameter; and
providing a third response to the user based on a result of performing the first task using the second parameter.
2. The method of claim 1 , further comprising, prior to performing the first task using the first parameter:
obtaining an initial text string from an initial speech input from the user;
identifying, based at least in part on the initial text string, the first task and the first parameter.
3. The method of claim 2 , further comprising, interpreting the initial text string to derive a first representation of user intent, wherein the identification of the first task and the first parameter is based at least in part on the first representation of user intent.
4. The method of claim 3 , further comprising:
prior to obtaining the initial text string, producing an output for presentation to the user based on the performing of the first task using the first parameter.
5. The method of claim 1 , wherein:
the first task is a telephone call;
the first parameter is a participant of the telephone call;
the second task is sending a text message; and
the performing the second task using the first parameter comprises sending the text message to the participant of the telephone call.
6. The method of claim 1 , wherein:
the first task is a weather forecast task;
the first parameter is a first location associated with the weather forecast;
the second parameter is a second location; and
the performing the first task using the second parameter comprises presenting a second weather forecast associated with the second location to the user.
7. The method of claim 1 , wherein the first parameter is a first geographic location, and wherein the second parameter is a second geographic location.
8. The method of claim 1 , wherein the first parameter is a first time, and wherein the second parameter is a second time.
9. The method of claim 1 , wherein the first task is a weather forecast task.
10. The method of claim 1 , wherein the first task is an event planning task.
11. The method of claim 1 , wherein the first task is a restaurant reservation task.
12. The method of claim 1 , wherein the first task is a constrained selection task.
13. A system for operating an intelligent automated assistant, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the processors to perform operations comprising:
performing a first task using a first parameter;
providing a first response to a user based on a result of performing the first task using the first parameter;
in a first operation:
obtaining a first text string from a first speech input received from the user;
determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and
in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter:
performing the second task using the first parameter; and
providing a second response to the user based on a result of performing the second task using the first parameter; and
in a second operation:
obtaining a second text string from a second speech input received from the user;
determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;
in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task:
performing the first task using the second parameter; and
providing a third response to the user based on a result of performing the first task using the second parameter.
14. The system of claim 13 , the operations further comprising, prior to performing the first task using the first parameter:
obtaining an initial text string from an initial speech input from the user;
identifying, based at least in part on the initial text string, the first task and the first parameter.
15. The system of claim 14 , the operations further comprising, interpreting the initial text string to derive a first representation of user intent, wherein the identification of the first task and the first parameter is based at least in part on the first representation of user intent.
16. The system of claim 15 , the operations further comprising:
prior to obtaining the initial text string, producing an output for presentation to the user based on the performing of the first task using the first parameter.
17. The system of claim 13 , wherein:
the first task is a telephone call;
the first parameter is a participant of the telephone call;
the second task is sending a text message; and
the performing the second task using the first parameter comprises sending the text message to the participant of the telephone call.
18. The system of claim 13 , wherein:
the first task is a weather forecast task;
the first parameter is a first location associated with the weather forecast;
the second parameter is a second location; and
the performing the first task using the second parameter comprises presenting a second weather forecast associated with the second location to the user.
19. The system of claim 13 , wherein the first parameter is a first geographic location, and wherein the second parameter is a second geographic location.
20. The system of claim 13 , wherein the first parameter is a first time, and wherein the second parameter is a second time.
21. The system of claim 13 , wherein the first task is a weather forecast task.
22. The system of claim 13 , wherein the first task is an event planning task.
23. The system of claim 13 , wherein the first task is a restaurant reservation task.
24. The system of claim 13 , wherein the first task is a constrained selection task.
25. A non-transitory computer readable storage medium storing instructions that, when executed by an electronic device with one or more processors, cause the processors to perform operations comprising:
performing a first task using a first parameter;
providing a first response to a user based on a result of performing the first task using the first parameter;
in a first operation:
obtaining a first text string from a first speech input received from the user;
determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and
in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter:
performing the second task using the first parameter; and
providing a second response to the user based on a result of performing the second task using the first parameter; and
in a second operation:
obtaining a second text string from a second speech input received from the user;
determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;
in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task:
performing the first task using the second parameter; and
providing a third response to the user based on a result of performing the first task using the second parameter.