| CPC G10L 15/222 (2013.01) [G06F 3/04842 (2013.01); G06F 9/485 (2013.01); G10L 25/51 (2013.01); G06F 9/461 (2013.01); G06F 9/4856 (2013.01); G06F 16/3325 (2019.01); G06F 16/90332 (2019.01); G06F 40/35 (2020.01); G10L 2015/223 (2013.01); G10L 2015/225 (2013.01); G10L 2015/228 (2013.01)] | 20 Claims |

|
1. A method implemented by one or more processors, the method comprising:
receiving natural language input from a user as part of a dialog session between the user and an automated assistant via an automated assistant interface of a client device of the user;
determining, based on processing the natural language input, an action to be performed by the automated assistant during the dialog session;
identifying, based on the action to be performed by the automated assistant during the dialog session, a third party agent for the automated assistant to engage with in furtherance of performing the action;
causing the automated assistant to engage with the third party agent in furtherance of performing the action;
while the automated assistant is engaged with the third party agent in furtherance of performing the action:
causing output to be provided for presentation to the user via the automated assistant interface of the client device of the user, the output requesting information to be utilized in furtherance of performing the action;
determining that no additional natural language input is received from the user subsequent to causing the output to be provided for presentation to the user; and
in response to determining that no additional natural language input is received from the user subsequent to causing the output to be provided for presentation to the user:
generating data that characterizes a state of the dialog session, the data that characterizes the state of the dialog session including a transcript of the dialog and an indication of the third party agent that engaged with the automated assistant in furtherance of performing the action; and
storing the data that characterizes the state of the dialog session; and
subsequent to storing the data that characterizes the state of the dialog session:
receiving a user selection of a given selectable icon associated with the dialog session via the automated assistant interface of the client device of the user, the given selectable icon being one of a plurality of disparate selectable icons that are displayed via the automated assistant interface of the client device of the user, and each of the plurality of disparate selectable icons being associated with a corresponding incomplete dialog session from among a plurality of incomplete dialog sessions that were previously conducted at the client device of the user;
in response to receiving the user selection of the selectable icon via the automated assistant interface of the client device of the user:
loading the data that characterizes the state of the dialog session, wherein loading the data that characterizes the state of the dialog session comprises:
causing the transcript of the dialog to be visually rendered via the automated assistant interface of the client device; and
causing the automated assistant to re-engage with the third party agent in furtherance of performing the action; and
receiving the additional natural language input from the user as part of the dialog session between the user and the automated assistant via the automated assistant interface of the client device of the user, the additional natural language input including the information to be utilized in furtherance of performing the action.
|