Synchronization and task delegation of a digital assistant
Systems and processes for operating an intelligent automated assistant are provided. In one example process, a first instance of a digital assistant operating on a first electronic device receives a natural-language speech input indicative of a user request. The first electronic device obtains a set of data corresponding to a second instance of the digital assistant on a second electronic device, and updates one or more settings of the first instance of the digital assistant based on the received set of data. The first instance of the digital assistant performs one or more tasks based on the updated one or more settings and provides an output indicative of whether the one or more tasks are performed.
1. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:
receive, by a first instance of a digital assistant operating on the electronic device, a natural-language speech input indicative of a user request;
obtain a set of data corresponding to a second instance of the digital assistant on a second electronic device including obtaining one or more settings used by the digital assistant to perform speech-to-text analysis and obtaining information associated with a previous user input, the previous user input comprising a user selection of a candidate application from a plurality of candidate applications, wherein the second electronic device is different from the electronic device;
update one or more settings of the first instance of the digital assistant based on the obtained set of data;
in response to receiving the user request, perform, by the first instance of the digital assistant, one or more tasks based on the updated one or more settings of the first instance of the digital assistant, wherein performing the one or more tasks includes performing speech-to-text analysis on the natural-language speech input based on the obtained one or more settings used by the digital assistant to perform speech-to-text analysis; and
provide, by the first instance of the digital assistant, an output indicative of whether the one or more tasks are performed.
2. The non-transitory computer-readable storage medium of claim 1 , wherein the electronic device and the second electronic device are associated with a same user.
3. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
obtaining one or more settings corresponding to the second instance of the digital assistant.
4. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
obtaining one or more language-related settings.
5. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
obtaining one or more settings related to a general preference of a user.
6. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
obtaining information corresponding to a set of suggestions, and
wherein the set of suggestions is related to a capability of the digital assistant.
7. The non-transitory computer-readable storage medium of claim 6 , wherein the information corresponds to one or more previous presentations of the set of suggestions by the second instance of the digital assistant.
8. The non-transitory computer-readable storage medium of claim 6 , wherein the information corresponds to one or more previous operations by a user on the second electronic device.
9. The non-transitory computer-readable storage medium of claim 6 , further comprising instructions, which when executed by one or more processors of the electronic device, cause the electronic device to:
at the electronic device:
determine, based on the obtained set of data, whether a predefined threshold is met for presenting the set of suggestions;
in accordance with a determination that the predefined threshold is met for presenting the set of suggestions, present, by the first instance of the digital assistant, the set of suggestions;
in accordance with a determination that the predefined threshold is not met for presenting the set of suggestions, foregoing presenting, by the first instance of the digital assistant, the set of suggestions.
10. The non-transitory computer-readable storage medium of claim 1 , wherein the set of data includes one or more settings related to a user-specific acoustic model.
11. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
obtaining information associated with a session between a user and the second instance of the digital assistant.
12. The non-transitory computer-readable storage medium of claim 11 , further comprising instructions, which when executed by one or more processors of the electronic device, cause the electronic device to:
at the electronic device:
determine, based on the natural-language input, whether the natural-language input corresponds to the session between the user and the second instance of the digital assistant;
provide, by the first instance of the digital assistant, an output based on the set of data.
13. The non-transitory computer-readable storage medium of claim 1 , wherein obtaining the set of data corresponding to the second instance of the digital assistant on the second electronic device comprises:
receiving, by the electronic device, the set of data from a server device different from the second electronic device.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the server device is a first server device, the non-transitory computer-readable storage medium further comprising instructions, which when executed by one or more processors of the electronic device, cause the electronic device to:
at the electronic device,
receive, from a second server device, a representation of user intent corresponding to the natural-language input, wherein the first server device is different from the second server device.
15. The non-transitory computer-readable storage medium of claim 14 , wherein at least a portion of the set of data is encrypted on the first server device.
16. The non-transitory computer-readable storage medium of claim 1 , wherein deriving the task based on the natural-language input comprises:
providing a text string based on the natural-language input;
determining, based on the text string, a representation of user intent; and
determining, based on the representation of user intent, a domain from a plurality of domains, wherein the determined domain is associated with the one or more tasks.
17. The non-transitory computer-readable storage medium of claim 1 , wherein the electronic device is a computer, a set-top box, a speaker, a smart watch, a phone, or any combination thereof.
18. The non-transitory computer-readable storage medium of claim 1 , wherein the second electronic device is a computer, a set-top box, a speaker, a smart watch, a phone, or any combination thereof.
19. The non-transitory computer-readable storage medium of claim 1 , wherein the one or more settings used by the digital assistant to perform speech-to-text analysis include information related to a user-specific acoustic model.
20. The non-transitory computer-readable storage medium of claim 1 , wherein the electronic device and the second electronic device are each client devices communicatively coupled to one or more server devices.
21. The non-transitory computer-readable storage medium of claim 19 , wherein the information related to the user-specific acoustic model is determined based on a user utterance received during a set-up process for the digital assistant.
22. 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, by a first instance of a digital assistant operating on the electronic device, a natural-language speech input indicative of a user request;
obtaining a set of data corresponding to a second instance of the digital assistant on a second electronic device including obtaining one or more settings used by the digital assistant to perform speech-to-text analysis and obtaining information associated with a previous user input, the previous user input comprising a user selection of a candidate application from a plurality of candidate applications, wherein the second electronic device is different from the electronic device;
updating one or more settings of the first instance of the digital assistant based on the obtained set of data;
in response to receiving the user request, performing, by the first instance of the digital assistant, one or more tasks based on the updated one or more settings of the first instance of the digital assistant, wherein performing the one or more tasks includes performing speech-to-text analysis on the natural-language speech input based on the obtained one or more settings used by the digital assistant to perform speech-to-text analysis; and
providing, by the first instance of the digital assistant, an output indicative of whether the one or more tasks are performed.
23. A method, comprising:
at a first electronic device with one or more processors and memory:
receiving, by a first instance of a digital assistant operating on the first electronic device, a natural-language speech input indicative of a user request;
obtaining a set of data corresponding to a second instance of the digital assistant on a second electronic device including obtaining one or more settings used by the digital assistant to perform speech-to-text analysis and obtaining information associated with a previous user input, the previous user input comprising a user selection of a candidate application from a plurality of candidate applications, wherein the second electronic device is different from the first electronic device;
updating one or more settings of the first instance of the digital assistant based on the obtained set of data;
in response to receiving the user request, performing, by the first instance of the digital assistant, one or more tasks based on the updated one or more settings of the first instance of the digital assistant, wherein performing the one or more tasks includes performing speech-to-text analysis on the natural-language speech input based on the obtained one or more settings used by the digital assistant to perform speech-to-text analysis; and
providing, by the first instance of the digital assistant, an output indicative of whether the one or more tasks are performed.