Initializing non-assistant background actions, via an automated assistant, while accessing a non-assistant application

A method of selecting an application to perform an action in response to processing of a spoken utterance by an automated assistant, the method implemented by one or more processors and comprising:

• determining, by a computing device that provides access to the automated assistant, that a user has provided one or more inputs for invoking the automated assistant,
• wherein the one or more inputs are provided by the user while the application is exhibiting a current application status;
• accessing, based on determining that the user has provided the one or more inputs, application data characterizing multiple different actions capable of being performed via one or more applications that include the application,
• wherein the application data characterizes contextual actions, including the action, that can be performed by the application when the application is exhibiting the current application status;
• identifying the spoken utterance that the user provided while the application is exhibiting the current application status,
• wherein the spoken utterance does not explicitly identify any application that is accessible via the computing device;
• determining whether there is a correlation between content of the spoken utterance and the application data;
• when there is a correlation between the content of the spoken utterance and the application data:
• selecting, based on the correlation, the action from the contextual actions characterized by the application data;
• causing, via the automated assistant, the application to perform the selected action;
• and
• when there is not a correlation between the content of the spoken utterance and the application data:
• causing, via the automated assistant, another application or the automated assistant to perform one or more other actions based on the spoken utterance.

A method of interacting with an automated assistant to cause action performance in response to an automated assistant receiving spoken input, the method implemented by one or more processors and comprising:

• receiving, from the automated assistant and while a user is accessing an application that is available via a computing device, an indication that the user has provided a spoken utterance,
• wherein the spoken utterance does not explicitly identify any application that is accessible via the computing device, and
• wherein the automated assistant is a separate application from the application that the user is accessing;
• providing, in response to receiving the indication that the user has provided the spoken utterance, application data that characterizes one or more contextual actions that can be performed by the application that the user is accessing,
• wherein the one or more contextual actions are identified by the application based on an ability of the application to initialize performance of the one or more contextual actions while the application is in a current state, and
• wherein the one or more contextual actions are selected from multiple different actions based on the current state of the application;
• causing, based on providing the application data, the automated assistant to determine whether the spoken utterance corresponds to a particular action of the one or more contextual actions characterized by the application data;
• and
• when the automated assistant determines that the spoken utterance corresponds to the particular action of the one or more contextual actions characterized by the application data and that can be performed by the application:
• cause performance of the particular action at the application.