Providing command bundle suggestions for an automated assistant
Generating and/or recommending command bundles for a user of an automated assistant. A command bundle comprises a plurality of discrete actions that can be performed by an automated assistant. One or more of the actions of a command bundle can cause transmission of a corresponding command and/or other data to one or more devices and/or agents that are distinct from devices and/or agents to which data is transmitted based on other action(s) of the bundle. Implementations determine command bundles that are likely relevant to a user, and present those command bundles as suggestions to the user. In some of those implementations, a machine learning model is utilized to generate a user action embedding for the user, and a command bundle embedding for each of a plurality of command bundles. Command bundle(s) can be selected for suggestion based on comparison of the user action embedding and the command bundle embeddings.
1. A method implemented by one or more processors, the method comprising:
causing a command bundle recommendation, for a given command bundle, to be displayed at a computing device of a particular user,
wherein causing the command bundle recommendation to be displayed is independent of receiving any query that indicates search criteria for command bundle recommendations,
wherein the given command bundle is created by an additional user, and
wherein the given command bundle comprises command bundle data that identifies a plurality of discrete actions that can be performed by an automated assistant, the discrete actions including a given action that includes a slot that lacks any fixed value;
receiving a selection at the computing device and from the particular user, the selection being of the displayed command bundle recommendation;
in response to receiving the selection:
engaging in interaction with the particular user and via the computing device of the particular user, to resolve a particular value for the slot that lacks any fixed value; and
assigning the given command bundle to the particular user, including storing the particular value in association with the at least one slot, for the given command bundle and for the particular user;
subsequent to assigning the given command bundle to the particular user:
determining to execute the given command bundle for the particular user; and
in response to determining to execute the given command bundle for the particular user:
performing the corresponding discrete actions of the given command bundle, including performing the given action using the particular value, for the slot, that was resolved in the interaction.
2. The method of claim 1 , wherein the given command bundle includes an invocation phrase for invoking the given command bundle, and wherein determining to execute the given command bundle for the particular user comprises:
processing spoken input, of the particular user, to determine that the spoken input includes the invocation phrase for the given command bundle; and
determining to execute the given command bundle for the particular user in response to determining that the spoken input includes the invocation phrase, for the given command bundle, and based on the given command bundle being assigned to the particular user.
3. The method of claim 1 , wherein the given command bundle includes one or more contextual conditions that, when satisfied, automatically invoke the given command bundle, and wherein determining to execute the given command bundle for the particular user comprises:
determining satisfaction of the one or more contextual conditions, for the particular user; and
automatically invoking the given command bundle, for the particular user, responsive to the determining satisfaction of the one or more contextual conditions, for the particular user, and based on the given command bundle being assigned to the particular user.
4. The method of claim 3 , wherein the one or more contextual conditions include a certain time window, a certain day of the week, and/or a location of a client device being within a geographic bound.
5. The method of claim 3 , wherein the one or more contextual conditions include two or more of: a certain time window, a certain day of the week, or a location of a client device being within a geographic bound.
6. The method of claim 1 , wherein the command bundle recommendation includes an invocation phrase for the given command bundle and an indication of the discrete actions of the given command bundle.
7. The method of claim 1 , wherein engaging in the interaction comprises:
providing a prompt to the particular user;
receiving natural language input in response to the prompt; and
resolving the particular value based on the natural language input.
8. The method of claim 7 , wherein the particular value specifies one or more Internet of things devices.
9. The method of claim 7 , wherein the particular value specifies a particular time of day.
10. The method of claim 1 , wherein causing the command bundle recommendation to be displayed at the computing device of the particular user is based on comparing command bundle data, for the given command bundle, to assistant interaction data for the particular user, the assistant interaction data indicating a plurality of historical actions performed for the particular user by the automated assistant.
11. The method of claim 1 , wherein the command bundle data comprises a command bundle embedding, and wherein comparing the command bundle data to the assistant interaction data for the particular user comprises:
generating a user action embedding based on processing at least part of the assistant interaction data for the particular user, and
comparing the user action embedding to the command bundle embedding.
12. A system, comprising:
memory storing instructions;
one or more processors are operable to execute the instructions to cause the one or more processors to:
cause a command bundle recommendation, for a given command bundle, to be displayed at a computing device of a particular user,
wherein causing the command bundle recommendation to be displayed is independent of receiving any query that indicates search criteria for command bundle recommendations,
wherein the given command bundle is created by an additional user, and
wherein the given command bundle comprises command bundle data that identifies a plurality of discrete actions that can be performed by an automated assistant, the discrete actions including a given action that includes a slot that lacks any fixed value;
receive a selection at the computing device and from the particular user, the selection being of the displayed command bundle recommendation;
in response to receiving the selection:
engage in interaction with the particular user and via the computing device of the particular user, to resolve a particular value for the slot that lacks any fixed value; and
assign the given command bundle to the particular user, wherein in assigning the given command bundle to the particular user one or more of the processors are to store the particular value in association with the at least one slot, for the given command bundle and for the particular user;
subsequent to assigning the given command bundle to the particular user:
determine to execute the given command bundle for the particular user; and
in response to determining to execute the given command bundle for the particular user:
perform the corresponding discrete actions of the given command bundle, including performing the given action using the particular value, for the slot, that was resolved in the interaction.
13. The system of claim 12 , wherein the given command bundle includes an invocation phrase for invoking the given command bundle, and wherein in determining to execute the given command bundle for the particular user one or more of the processors are to:
process spoken input, of the particular user, to determine that the spoken input includes the invocation phrase for the given command bundle; and
determine to execute the given command bundle for the particular user in response to determining that the spoken input includes the invocation phrase, for the given command bundle, and based on the given command bundle being assigned to the particular user.
14. The system of claim 12 , wherein the given command bundle includes one or more contextual conditions that, when satisfied, automatically invoke the given command bundle, and wherein in determining to execute the given command bundle for the particular user one or more of the processors are to:
determine satisfaction of the one or more contextual conditions, for the particular user; and
automatically invoke the given command bundle, for the particular user, responsive to the determining satisfaction of the one or more contextual conditions, for the particular user, and based on the given command bundle being assigned to the particular user.
15. The system of claim 14 , wherein the one or more contextual conditions include a certain time window, a certain day of the week, and/or a location of a client device being within a geographic bound.
16. The system of claim 12 , wherein the command bundle recommendation includes an invocation phrase for the given command bundle and an indication of the discrete actions of the given command bundle.
17. The system of claim 16 , wherein engaging in the interaction comprises:
providing a prompt to the particular user;
receiving natural language input in response to the prompt; and
resolving the particular value based on the natural language input.
18. The system of claim 17 , wherein the particular value specifies one or more Internet of things devices.
19. The system of claim 17 , wherein the particular value specifies a particular time of day.
20. The system of claim 12 , wherein causing the command bundle recommendation to be displayed at the computing device of the particular user is based on comparing command bundle data, for the given command bundle, to assistant interaction data for the particular user, the assistant interaction data indicating a plurality of historical actions performed for the particular user by the automated assistant.