Regulating assistant responsiveness according to characteristics of a multi-assistant environment
Implementations set forth herein relate to employing dynamic regulations for governing responsiveness of multiple automated assistant devices, and specifically the responsiveness an automated assistant to a given spoken utterance that has been acknowledged by two or more of the assistant devices. The dynamic regulations can be context-dependent and adapted over time in order that the automated assistant can accommodate assistant interaction preferences that may vary from user to user. For instance, a spoken utterance such as “stop,” may be intended to affect different assistant actions based on a context in which the user provided the spoken utterance. The context can refer to a location of the user relative to other rooms in a home, a time of day, a user providing the spoken utterance, an arrangement of the assistant devices within a home, and/or a state of each device in the home.
1. A method implemented by one or more processors, the method comprising:
storing a plurality of dynamic regulations in a database, each dynamic regulation associated with a user command, and specifying a correspondence between each of a plurality of controlled devices to perform an action corresponding to the user command, and contextual information for the user and/or at least one of the plurality of client devices including the respective controlled device;
training the stored plurality of regulations by:
receiving a first input representing a user command from one of a plurality of client devices,
identifying one of the plurality of stored dynamic regulations corresponding to the received user command,
requesting and obtaining contextual information for the user and/or at least one of the plurality of client devices including the controlled device,
identifying a client device of the plurality of client devices as the controlled device based on the contextual information associated with the stored dynamic regulation,
initiating execution of the identified dynamic regulation by the identified client device,
receiving a second input representing an update of the user command from the one of the plurality of client devices, the correction specifying an updated client device to be controlled, and
updating the stored dynamic regulation in the database to specify correspondence between the updated client device and the obtained contextual information, wherein the updated stored dynamic regulation causes identifying of the updated client device in response to a subsequent input that represents the user command and that is received when the contextual information is again present; and
initiating execution of the identified dynamic regulation by the updated client device.
2. The method of claim 1 , wherein requesting and obtaining the contextual information for the user and/or the at least one of the plurality of client devices comprises:
requesting and obtaining a location of the user within an area containing one or more of the plurality of client devices.
3. The method of claim 2 , wherein requesting and obtaining the location of the user further comprises requesting and obtaining a trajectory of the user, wherein the trajectory of the user indicates a movement of the user between the area containing one or more of the plurality of client devices and an additional area.
4. The method of claim 1 , wherein requesting and obtaining the contextual information for the user and/or the at least one of the plurality of client devices comprises:
requesting and obtaining a location corresponding to each of the client devices of the plurality of client devices.
5. The method of claim 1 , wherein the first input representing the user command from one of the plurality of client devices comprises a spoken utterance spoken by the user identifying the user command.
6. The method of claim 5 , wherein the second input representing the update of the user command comprises an additional spoken utterance spoken by the user specifying the updated client device to be controlled.
7. A system comprising:
a database storing a plurality of dynamic regulations, each dynamic regulation associated with a user command, and specifying a correspondence between each of a plurality of controlled devices to perform an action corresponding to the user command, and contextual information for the user and/or at least one of the plurality of client devices including the respective controlled device;
one or more processors operable to:
update the stored plurality of regulations, wherein in updating the stored plurality of regulations one or more of the processors are to:
receive a first input representing a user command from one of a plurality of client devices,
identify one of the plurality of stored dynamic regulations corresponding to the received user command,
request and obtaining contextual information for the user and/or at least one of the plurality of client devices including the controlled device,
identify a client device of the plurality of client devices as the controlled device based on the contextual information associated with the stored dynamic regulation,
initiate execution of the identified dynamic regulation by the identified client device,
receive a second input representing an update of the user command from the one of the plurality of client devices, the correction specifying an updated client device to be controlled, and
update the stored dynamic regulation in the database to specify correspondence between the updated client device and the obtained contextual information; and
subsequent to updating the stored dynamic regulation in the database:
use the updated dynamic regulation in identifying the updated client device in response to a subsequent input that represents the user command and that is received when the contextual information is again present.
8. The system of claim 7 , wherein in requesting and obtaining the contextual information for the user and/or the at least one of the plurality of client devices, one or more of the processors are to:
request and obtain a location of the user within an area containing one or more of the plurality of client devices.
9. The system of claim 8 , wherein in requesting and obtaining the location of the user one or more of the processors are further to request and obtain a trajectory of the user, wherein the trajectory of the user indicates a movement of the user between the area containing one or more of the plurality of client devices and an additional area.
10. The system of claim 7 , wherein in requesting and obtaining the contextual information for the user and/or the at least one of the plurality of client devices one or more of the processors are to:
request and obtain a location corresponding to each of the client devices of the plurality of client devices.
11. The system of claim 7 , wherein the first input representing the user command from one of the plurality of client devices comprises a spoken utterance spoken by the user identifying the user command.
12. The system of claim 7 , wherein the second input representing the update of the user command comprises an additional spoken utterance spoken by the user specifying the updated client device to be controlled.
13. 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:
storing a plurality of dynamic regulations in a database, each dynamic regulation associated with a user command, and specifying a correspondence between each of a plurality of controlled devices to perform an action corresponding to the user command, and contextual information for the user and/or at least one of the plurality of client devices including the respective controlled device;
training the stored plurality of regulations by:
receiving a first input representing a user command from one of a plurality of client devices,
identifying one of the plurality of stored dynamic regulations corresponding to the received user command,
requesting and obtaining contextual information for the user and/or at least one of the plurality of client devices including the controlled device,
identifying a client device of the plurality of client devices as the controlled device based on the contextual information associated with the stored dynamic regulation,
initiating execution of the identified dynamic regulation by the identified client device,
receiving a second input representing an update of the user command from the one of the plurality of client devices, the correction specifying an updated client device to be controlled, and
updating the stored dynamic regulation in the database to specify correspondence between the updated client device and the obtained contextual information, wherein the updated stored dynamic regulation causes identifying of the updated client device in response to a subsequent input that represents the user command and that is received when the contextual information is again present; and
initiating execution of the identified dynamic regulation by the updated client device.