Providing suggested voice-based action queries
Technology of the disclosure may facilitate user discovery of various voice-based action queries that can be spoken to initiate computer-based actions, such as voice-based action queries that can be provided as spoken input to a computing device to initiate computer-based actions that are particularized to content being viewed or otherwise consumed by the user on the computing device. Some implementations are generally directed to determining, in view of content recently viewed by a user on a computing device, at least one suggested voice-based action query for presentation via the computing device. Some implementations are additionally or alternatively generally directed to receiving at least one suggested voice-based action query at a computing device and providing the suggested voice-based action query as a suggestion in response to input to initiate providing of a voice-based query via the computing device.
1. A method implemented by one or more processors, the method comprising:
receiving, while a first application of a computing device is displaying content, an input to initiate providing of a voice-based query via the computing device;
generating, based on the content currently being displayed by the first application, a suggested voice-based action query that can be spoken to initiate performance of a computer-based action;
in response to receiving the input to initiate providing of the voice-based query:
causing a second application of the computing device to:
monitor for voice input,
display an indication of awaiting spoken input, and
while monitoring for voice input and displaying the indication of awaiting spoken input:
display an interface element over the content currently being displayed by the first application, wherein the interface element includes a selectable display of the generated suggested voice-based action query;
in response to receiving a selection of the selectable display of the suggested voice-based action query:
causing performance of the computer-based action of the suggested voice-based action query.
2. The method of claim 1 , wherein the input to initiate providing of a voice-based query is a spoken phrase, an actuation of a touch-sensitive hardware element of the computing device, or performing a gesture in view of a camera of the computing device.
3. The method of claim 1 , wherein performance of the computer-based action is by a third application of the computing device.
4. The method of claim 3 , wherein generating the suggested voice-based action query is based on the third application being installed on the computing device, and based on the computer-based action being mapped to the third application.
5. The method of claim 4 , wherein generating the suggested voice-based action query is based on a version of the third application that is installed on the computing device, and based on the computer-based action being mapped to the version of the third application.
6. The method of claim 1 , wherein generating the suggested voice-based action query based on the content currently being displayed by the first application comprises:
determining an entity referenced in the content;
determining the computer-based action is mapped to the entity in one or more electronic databases; and
generating the suggested voice-based action query to include at least one term that initiates performance of the computer based action and to include at least one entity term selected based on the entity.
7. The method of claim 6 , wherein generating the suggested voice-based action query comprises determining a pronoun mapped to the entity, and using the pronoun as the at least one entity term.
8. The method of claim 6 , wherein generating the suggested voice-based action query comprises determining a preferred language of the computing device, and generating the suggested voice-based action query based on the preferred language of the computing device.
9. The method of claim 1 , wherein the second application is integrated as part of an operating system of the computing device.
10. The method of claim 1 , wherein including the selectable display of the suggested voice-based action query in the interface element is based on detecting at least a threshold noise level by the computing device following the input of the user to initiate providing of the voice-based action query.
11. The method of claim 1 , wherein including the selectable display of the suggested voice-based action query in the interface element is based on detecting that no spoken input has been received within a threshold amount of time following the input of the user to initiate providing of the voice-based action query.
12. A system, comprising:
one or more processors; and
memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to:
receive, while a first application is displaying content, an input to initiate providing of a voice-based query;
generate, based on the content currently being displayed by the first application, a suggested voice-based action query that can be spoken to initiate performance of a computer-based action;
in response to receiving the input to initiate providing of the voice-based query:
cause a second application to:
monitor for voice input,
display an indication of awaiting spoken input, and
while monitoring for voice input and displaying the indication of awaiting spoken input:
display an interface element over the content currently being displayed by the first application, wherein the interface element includes a selectable display of the generated suggested voice-based action query;
in response to receiving a selection of the selectable display of the suggested voice-based action query:
cause performance of the computer-based action of the suggested voice-based action query.