Initializing a conversation with an automated agent via selectable graphical element
Methods, apparatus, systems, and computer-readable media are provided for using selectable elements to invoke an automated assistant at a computing device. While operating the computing device, a user may not be aware that the automated assistant can be invoked according to certain invocation phrases. In order to inform the user of the functionality of the automated assistant, the user can be presented with selectable elements that can initialize the automated assistant when selected. Furthermore, a selectable element can provide an invocation phrase in textual form so that the user is aware of their ability to invoke the automated assistant by speaking the invocation phrase. The selectable element can be presented at different devices associated with the user, and the automated assistant can be initialized at a device that is separate from the device where the selectable element is presented.
1 . A method implemented by one or more processors, the method comprising:
identifying, using credentials for a user, multiple computing devices associated with the credentials, the multiple computing devices including a first computing device, a second computing device, and a third computing device;
determining an automated assistant operation that is to be performed;
in response to determining the automated assistant operation:
selecting, from the multiple computing devices and based on the automated assistant operation, the second computing device for the automated assistant operation; and
causing the first computing device to visually render, at a graphical user interface of the first computing device:
a second selectable element with a second representation of the second computing device,
wherein the second selectable element with the second representation of the second computing device is rendered responsive to selecting the second computing device for the automated assistant operation; and
wherein the second selectable element includes text that identifies the operation that is to be performed by the second computing device;
determining occurrence of a selection, via the graphical user interface, of the second selectable element; and
in response to determining the occurrence of the selection of the second selectable element:
causing the automated assistant operation to be performed at the second computing device, and
providing an additional selectable element at a second graphical user interface of the second computing device, the additional selectable element being selectable via a spoken utterance provided by the user to cause the automated assistant at the second computing device to perform one or more additional operations.
2 . The method of claim 1 , further comprising, subsequent to causing the automated assistant operation to be performed at the second computing device:
determining an additional automated assistant operation that is to be performed;
in response to determining the additional automated assistant operation:
selecting, from the multiple computing devices and based on the additional automated assistant operation, the third computing device for the additional automated assistant operation; and
causing the first computing device to visually render, at the graphical user interface of the first computing device:
a third selectable element with a third representation of the third computing device,
wherein the third selectable element with the third representation of the third computing device is rendered responsive to selecting the third computing device for the additional automated assistant operation.
3 . The method of claim 2 , further comprising:
determining occurrence of an additional selection, via the graphical user interface, of the third selectable element; and
in response to determining the occurrence of the additional selection of the third selectable element:
causing the additional automated assistant operation to be performed at the third computing device.
4 . The method of claim 1 , wherein causing the automated assistant operation to be performed at the second computing device causes an automated assistant interface of the second computing device to perform the automated assistant operation and to transition to a state in which monitoring, at the automated assistant interface of the second computing device, for one or more spoken utterances occurs.
5 . The method of claim 1 , wherein causing the automated assistant operation to be performed at the second computing device causes an automated assistant interface of the second computing device to perform the automated assistant operation and to provide one or more additional selectable elements at the automated assistant interface of the second computing device, the one or more additional selectable elements being selectable to cause performance of one or more additional automated assistant operations.
6 . The method of claim 1 , wherein the second selectable element is displayed at the graphical user interface along with a command phrase that includes natural language content, which, when provided as a spoken input to an automated assistant interface of the second computing device, causes the automated assistant operation to be performed at the second computing device.
7 . The method of claim 6 , further comprising generating the command phrase based on historical data for the user.
8 . The method of claim 1 , wherein the automated assistant operation, when performed, causes providing of a response.
9 . The method of claim 8 , wherein the response comprises an audible response.
10 . A system comprising:
memory storing instructions; and
one or more processors operable to execute the instructions to:
identify multiple computing devices associated with a user, the multiple computing devices including a first computing device, a second computing device, and a third computing device;
determine an automated assistant operation that is to be performed;
in response to determining the automated assistant operation:
select, from the multiple computing devices and based on the automated assistant operation, the second computing device for the automated assistant operation; and
cause the first computing device to visually render, at a graphical user interface of the first computing device:
a second selectable element with a second representation of the second computing device, wherein the second selectable element with the second representation of the second computing device is rendered responsive to selecting the second computing device for the automated assistant operation; and wherein the second selectable element includes text that identifies the operation that is to be performed by the second computing device;
determine occurrence of a selection, via the graphical user interface, of the second selectable element; and
in response to determining the occurrence of the selection of the second selectable element:
cause the automated assistant operation to be performed at the second computing device, and
provide an additional selectable element at a second graphical user interface of the second computing device, the additional selectable element being selectable via a spoken utterance provided by the user to cause the automated assistant at the second computing device to perform one or more additional operations.
11 . The system of claim 10 , wherein one or more of the processors are further operable to execute the instructions to, subsequent to causing the automated assistant operation to be performed at the second computing device:
determine an additional automated assistant operation that is to be performed;
in response to determining the additional automated assistant operation:
select, from the multiple computing devices and based on the additional automated assistant operation, the third computing device for the additional automated assistant operation; and
cause the first computing device to visually render, at the graphical user interface of the first computing device:
a third selectable element with a third representation of the third computing device,
wherein the third selectable element with the third representation of the third computing device is rendered responsive to selecting the third computing device for the additional automated assistant operation.
12 . The system of claim 11 , wherein one or more of the processors are further operable to execute the instructions to:
determine occurrence of an additional selection, via the graphical user interface, of the third selectable element; and
in response to determining the occurrence of the additional selection of the third selectable element:
cause the additional automated assistant operation to be performed at the third computing device.
13 . The system of claim 10 , wherein causing the automated assistant operation to be performed at the second computing device causes an automated assistant interface of the second computing device to perform the automated assistant operation and to transition to a state in which monitoring, at the automated assistant interface of the second computing device, for one or more spoken utterances occurs.
14 . The system of claim 10 , wherein causing the automated assistant operation to be performed at the second computing device causes an automated assistant interface of the second computing device to perform the automated assistant operation and to provide one or more additional selectable elements at the automated assistant interface of the second computing device, the one or more additional selectable elements being selectable to cause performance of one or more additional automated assistant operations.
15 . The system of claim 10 , wherein the second selectable element is displayed at the graphical user interface along with a command phrase that includes natural language content, which, when provided as a spoken input to an automated assistant interface of the second computing device, causes the automated assistant operation to be performed at the second computing device.
16 . The system of claim 15 , wherein one or more of the processors are further operable to execute the instructions to generate the command phrase based on historical data for the user.
17 . The system of claim 10 , wherein the automated assistant operation, when performed, causes providing of a response.
18 . The system of claim 17 , wherein the response comprises an audible response.
19 . At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:
identifying, using credentials for a user, multiple computing devices associated with the credentials, the multiple computing devices including a first computing device, a second computing device, and a third computing device;
determining an automated assistant operation that is to be performed;
in response to determining the automated assistant operation:
selecting, from the multiple computing devices and based on the automated assistant operation, the second computing device for the automated assistant operation; and
causing the first computing device to visually render, at a graphical user interface of the first computing device:
a second selectable element with a second representation of the second computing device,
wherein the second selectable element with the second representation of the second computing device is rendered responsive to selecting the second computing device for the automated assistant operation; and
wherein the second selectable element includes text that identifies the operation that is to be performed by the second computing device;
determining occurrence of a selection, via the graphical user interface, of the second selectable element; and
in response to determining the occurrence of the selection of the second selectable element:
causing the automated assistant operation to be performed at the second computing device, and
providing an additional selectable element at a second graphical user interface of the second computing device, the additional selectable element being selectable via a spoken utterance provided by the user to cause the automated assistant at the second computing device to perform one or more additional operations.