Discovering capabilities of third-party voice-enabled resources
US-2016189717-A1 · Jun 30, 2016 · US
US10152299B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10152299-B2 |
| Application number | US-201514839643-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 28, 2015 |
| Priority date | Mar 6, 2015 |
| Publication date | Dec 11, 2018 |
| Grant date | Dec 11, 2018 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and processes for reducing response latency of intelligent automated assistants are provided. In one example process, a speech input containing a user request can be received from a user. A representation of the speech input can be transmitted. A domain signal representing a relevant domain associated with the user request can be received. The process can determine whether the relevant domain is associated with a predefined action of a set of predefined actions. In response to determining that the relevant domain is associated with a predefined action of a set of predefined actions, the predefined action can be performed. Data content relevant to satisfying the user request can be received. A result based on the data content can be outputted to at least partially satisfy the user request.
Opening claim text (preview).
What is claimed is: 1. A method for reducing response latency of intelligent automated assistants, the method comprising: at an electronic device: receiving, from a user, a speech input containing a user request; transmitting, to a server, a representation of the speech input; receiving, from the server, a domain signal defining a relevant domain of an actionable intent inferred from the user request; determining whether the relevant domain is associated with a predefined action of a set of predefined actions supported by the electronic device; in response to determining that the relevant domain is associated with a predefined action on the electronic device, performing the predefined action; after at least partially performing the predefined action, receiving, from the server, data content relevant to satisfying the user request, wherein the data content is generated according to an executed task flow corresponding to the actionable intent, and wherein performing the predefined action at least partially prepares the electronic device to process the received data content; and outputting a result based on the data content to at least partially satisfy the user request. 2. The method of claim 1 , further comprising processing the data content to obtain the result, wherein performing the predefined action is prerequisite to processing the data content. 3. The method of claim 1 , further comprising performing a task based on the data content to obtain the result, wherein performing the predefined action is prerequisite to performing the task. 4. The method of claim 1 , further comprising: in response to determining that the relevant domain is not associated with any predefined action of the set of predefined actions supported by the electronic device, performing a task based on the data content. 5. The method of claim 4 , wherein the performed task is in accordance with instructions provided in the data content. 6. The method of claim 4 , wherein the result is obtained from performing the task. 7. The method of claim 1 , wherein the relevant domain is a domain of a domain-specific ontology that is relevant to the user request. 8. The method of claim 1 , wherein the predefined action comprises loading an application associated with the relevant domain to operate in a background mode, and wherein in response to determining that the relevant domain is associated with the predefined action: loading the application from a memory of the electronic device to operate in a background mode on the electronic device. 9. The method of claim 8 , further comprising: in response to determining that the relevant domain is associated with the predefined action: determining that the data content is associated with the application; and directing the data content to the application while the application is operating in the background mode. 10. The method of claim 8 , further comprising: in response to determining that the relevant domain is associated with the predefined action: processing the data content using the application while the application is operating in the background mode to obtain the result. 11. The method of claim 8 , wherein in response to determining that the relevant domain is associated with the predefined action, outputting the result includes: changing an operating mode of the application from the background mode to an active mode; and displaying the result on the electronic device via a graphic user interface of the application while the application is operating in the active mode. 12. The method of claim 1 , wherein the set of predefined actions is associated with a set of applications on the electronic device, and further comprising: in response to determining that the relevant domain is not associated with any predefined action of the set of predefined actions: determining that the data content is associated with a second application of the electronic device, wherein the set of applications does not include the second application; and processing the data content using the second application to obtain the result. 13. The method of claim 12 , further comprising: in response to determining that the relevant domain is not associated with any predefined action of the set of predefined actions, and in response to determining that the data content is associated with the second application: determining whether the second application is operating on the electronic device; in response to determining that the second application is not operating on the electronic device: loading the second application from the memory of the electronic device to operate the second application in a background mode; and directing the data content to the second application while the second application operations in the background mode. 14. The method of claim 13 , further comprising: in response to determining that the second application is operating on the electronic device, directing the data content to the second application. 15. The method of claim 12 , wherein in response to determining that the relevant domain is not associated with any predefined action of the set of predefined actions, outputting the result includes: changing an operating mode of the second application from the background mode to an active mode; and displaying the result on the electronic device via a graphic user interface of the second application while the second application is operating in the active mode. 16. The method of claim 1 , further comprising: determining whether the electronic device is communicatively coupled to a second electronic device, wherein in response to determining that the electronic device is communicatively coupled to the second electronic device: the representation of the speech input is transmitted to the server via the second electronic device; the domain signal is received from the server via the second electronic device; and the data content is received from the server via the second electronic device. 17. The method of claim 16 , wherein determining whether the electronic device is communicatively coupled to a second electronic device is performed prior to transmitting the representation of the speech input. 18. The method of claim 16 , wherein in response to determining that the electronic device is not communicatively coupled to the second electronic device: the representation of the speech input is transmitted directly to a server; the domain signal is received directly from the server; and the data content is received directly from the server. 19. The method of claim 1 , further comprising: receiving, from the server, a second domain signal identifying a second relevant domain associated with the user request; determining whether the second relevant domain is associated with a second predefined action of the set of predefined actions supported by the electronic device; and in response to determining that the relevant domain is associated with a second predefined action of the set of predefined actions, performing the second predefined action. 20. The method of claim 1 , wherein the domain signal further identifies a second relevant domain associated with the user request, and further comprising: determining whether the second relevant domain is associated with a second predefined action of the set of predefined actions supported by the electronic device; and in response to determining that the relevant domain is associated with a second predefined action of the se
Physics · mapped topic
using context dependencies, e.g. language models · CPC title
for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title
Physics · mapped topic
in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.