Systems, methods, and apparatuses for providing assistant deep links to effectuate third-party dialog session transfers
Methods, apparatus, systems, and computer-readable media are provided for transferring dialog sessions between devices using deep links. The dialog sessions can correspond to interactions, mediated by an automated assistant, between a user and a third party application. During the dialog session, a user can request that the dialog session be transferred to a different device, for example, to interact with the third party application through a different modality. In response, the automated assistant and/or the third party application can generate a link that can be transferred to the transferee device to allow the transferee device to seamlessly take over the dialog session. In this way, computational resources and electrical power can be preserved by not requiring a recipient device to re-process natural language inputs previously provided during the dialog session.
1 . A method implemented by one or more processors, the method comprising:
generating, at a first client device, interaction data based on a dialog session between a user and a third party application, wherein:
the dialog session is mediated by a machine learning model accessible to the first client device and a second client device, and
the interaction data identifies an action that, when executed by the third party application, causes content to be provided at an interface of the first client device;
receiving, at the first client device, a natural language input for requesting that the dialog session between the user and the third party application be continued at the second client device;
identifying one or more links based on the interaction data, wherein each link of the one or more links is associated with a set of one or more modalities for presenting output generated by the third party application;
providing the one or more links to the second client device, wherein the second client device engages with the third party application using the one or more links; and
causing the output to be rendered, based on the one or more links, via a user interface of the second client device.
2 . The method of claim 1 , wherein each link, of the one or more links is generated based on the interaction data in response to the first client device receiving natural language input.
3 . The method of claim 1 , wherein each link, of the one or more links is generated based on the interaction data in response to receiving the natural language input request that the dialog session be continued at the second client device.
4 . The method of claim 3 , wherein the one or more links identify selectable content to be provided at the second client device.
5 . The method of claim 1 , wherein, in engaging with the third party application using the one or more links, the second client device causes an instance of the third party application to be initiated at the second client device.
6 . The method of claim 1 , wherein, in engaging with the third party application using the one or more links, the second client device causes a download of the third party application to be initiated at the second client device.
7 . A non-transitory computer readable storage medium configured to store instructions that, when executed by one or more processors, cause the one or more processors to perform operations that include:
generating, at a first client device, interaction data based on a dialog session between a user and a third party application, wherein:
the dialog session is mediated by a machine learning model accessible to the first client device and a second client device, and
the interaction data identifies an action that, when executed by the third party application, causes content to be provided at an interface of the first client device;
receiving, at the first client device, a natural language input for requesting that the dialog session between the user and the third party application be continued at the second client device;
identifying one or more links based on the interaction data, wherein each link of the one or more links is associated with a set of one or more modalities for presenting output generated by the third party application;
providing the one or more links to the second client device, wherein the second client device engages with the third party application using the one or more links; and
causing the output to be rendered, based on the one or more links, via a user interface of the second client device.
8 . The non-transitory computer readable storage medium of claim 7 , wherein each link, of the one or more links is generated based on the interaction data in response to the first client device receiving natural language input.
9 . The non-transitory computer readable storage medium of claim 7 , wherein each link, of the one or more links is generated based on the interaction data in response to receiving the natural language input request that the dialog session be continued at the second client device.
10 . The non-transitory computer readable storage medium of claim 9 , wherein the one or more links identify selectable content to be provided at the second client device.
11 . The non-transitory computer readable storage medium of claim 7 , wherein, in engaging with the third party application using the one or more links, the second client device causes an instance of the third party application to be initiated at the second client device.
12 . The non-transitory computer readable storage medium of claim 7 , wherein, in engaging with the third party application using the one or more links, the second client device causes a download of the third party application to be initiated at the second client device.
13 . A system comprising:
one or more processors; and
memory configured to store instructions that, when executed by the one or more processors cause the one or more processors to perform operations that include:
generating, at a first client device, interaction data based on a dialog session between a user and a third party application, wherein:
the dialog session is mediated by a machine learning model accessible to the first client device and a second client device, and
the interaction data identifies an action that, when executed by the third party application, causes content to be provided at an interface of the first client device;
receiving, at the first client device, a natural language input for requesting that the dialog session between the user and the third party application be continued at the second client device;
identifying one or more links based on the interaction data, wherein each link of the one or more links is associated with a set of one or more modalities for presenting output generated by the third party application;
providing the one or more links to the second client device, wherein the second client device engages with the third party application using the one or more links; and
causing the output to be rendered, based on the one or more links, via a user interface of the second client device.
14 . The system of claim 13 , wherein each link, of the one or more links is generated based on the interaction data in response to the first client device receiving natural language input.
15 . The system of claim 13 , wherein each link, of the one or more links is generated based on the interaction data in response to receiving the natural language input request that the dialog session be continued at the second client device.
16 . The system of claim 13 , wherein the one or more links identify selectable content to be provided at the second client device.
17 . The system of claim 13 , wherein, in engaging with the third party application using the one or more links, the second client device causes an instance of the third party application to be initiated at the second client device.
18 . The system of claim 13 , wherein, in engaging with the third party application using the one or more links, the second client device causes a download of the third party application to be initiated at the second client device.