Systems and methods for voice-based initiation of custom device actions

1. A data processing system to provide content responsive to voice-based interactions, comprising:

a memory to store (i) first device action data including a first plurality of device action-command pairs supported by a first plurality of remote electronic devices and defined by a provider of the first plurality of remote electronic devices, and (ii) second device action data including a second plurality of device action-command pairs supported by a second plurality of remote electronic devices and defined by a provider of the second plurality of remote electronic devices, each device action-command pair including a respective device action of a plurality of device actions and a respective device executable command of a plurality of device executable commands to trigger performance of the respective device action;

a device action customization component to maintain a first mapping between a first identifier and the first device action data, and maintain a second mapping between a second identifier and the second device action data;

a communications interface to receive, from a remote electronic device of the first plurality of remote electronic devices, an audio signal and the first identifier, the audio signal obtained by the remote electronic device responsive to a voice-based query;

the device action customization component to identify, responsive to receipt of the audio signal and the first identifier, the first device action data using the first mapping between the first identifier and the first device action data;

a natural language processor component to identify, responsive to identifying the first device action data and using content associated with the audio signal, a device action-command pair of the first plurality of device action-command pairs in the first device action data, the device action-command pair including a first device action and a first command;

the device action customization component to identify, using the first device action associated with the device-action command pair, a predefined sequence of device actions associated with the voice-based query, the predefined sequence of device actions including one or more second device actions to be performed subsequent to the first device action;

the device action customization component to identify a context of the voice-based query based on the one or more second device actions to be performed subsequent to the first device action;

a content selector component to select, based on the context of the voice-based query, a third-party content item for presentation by the remote electronic device; and

the communications interface to transmit the third-party content item and the first command associated with the device action-command pair to the remote electronic device, the first command to cause performance of the device action associated with the device action-command pair.

2. The data processing system of claim 1 , wherein the third-party content item includes an audio digital component.

3. The data processing system of claim 1 , comprising:

the memory to maintain a first plurality of responses for serving to the first plurality of remote electronic devices, each response of the first plurality of responses mapped to a corresponding device-action pair of the first plurality of device-action pairs supported by the first plurality of remote electronic devices;

the device action customization component to identify a response of the first plurality of responses corresponding to the device action-command pair; and

the communications interface to transmit the response to the remote electronic device for presentation.

4. The data processing system of claim 1 , comprising:

the memory to maintain, for each device action-command pair of the first plurality of device action-command pairs, one or more corresponding keywords; and

the device action customization component to identify the context of the voice-based query based on the one or more keywords associated with the device action-command pair identified by the natural language processor component.

5. The data processing system of claim 1 , wherein the first identifier includes a device model identifier (ID) indicative of a device model of the first plurality of remote electronic devices and the first plurality of device action-command pairs are specific to the device model.

6. The data processing system of claim 5 comprising:

the memory to maintain a description of the first plurality of remote electronic devices associated with the device model; and

the device action customization component to identify an attribute of the context of the voice-based query based on the description of the first plurality of remote electronic devices associated with device model.

7. The data processing system of claim 1 , wherein the first identifier includes an identifier associated with an application installed on the first plurality of remote electronic devices and the first plurality of device action-command pairs are specific to the application.

8. The data processing system of claim 7 comprising:

the memory to maintain a description of the application installed on the first plurality of remote electronic devices; and

the device action customization component to identify an attribute of the context of the voice-based query based on the description of the application installed on the first plurality of remote electronic devices.

9. The data processing system of claim 1 comprising:

the device action customization component to identify one or more parameter values of the first command associated with the device action-command pair; and

the device action customization component to identify an attribute of the context of the voice-based query based on the one or more parameter values of the first command associated with the device action-command pair.

10. The data processing system of claim 1 , comprising:

the device action customization component to provide a user interface to allow transmission of the first and second device action data and the first and second identifiers to the data processing system.

11. The data processing system of claim 1 , comprising:

the device action customization component to provide a restful application programming interface (API) to allow transmission of the first and second device action data and the first and second identifiers to the data processing system.

12. A method of providing content responsive to voice-based interactions, the method comprising:

storing, in a memory, (i) first device action data including a first plurality of device action-command pairs supported by a first plurality of remote electronic devices and defined by a provider of the first plurality of remote electronic devices, and (ii) second device action data including a second plurality of device action-command pairs supported by a second plurality of remote electronic devices and defined by a provider of the second plurality of remote electronic devices, each device action-command pair including a respective device action of a plurality of device actions and a respective device executable command of a plurality of device executable commands to trigger performance of the respective device action;

maintaining a first mapping between a first identifier and the first device action data, and a second mapping between a second identifier and the second device action data;

receiving, from a remote electronic device of the first plurality of remote electronic devices, an audio signal and the first identifier, the audio signal obtained by the remote electronic device responsive to a voice-based query;

identifying, responsive to receipt of the audio signal and the first identifier, the first device action data using the first mapping between the first identifier and the first device action data;

identifying, responsive to identifying the first device action data and using content associated with the audio signal, a device action-command pair of the first plurality of device action-command pairs in the first device action data, the device action-command pair including a first device action and a first command;

identifying, using the first device action associated with the device-action command pair, a predefined sequence of device actions associated with the voice-based query, the predefined sequence of device actions including one or more second device actions to be performed subsequent to the first device action;

identifying a context of the voice-based query based on the one or more second device actions to be performed subsequent to the first device action;

selecting, based on the context of the voice-based query, a third-party content item for presentation by the remote electronic device; and

transmitting the third-party content item and the first command associated with the device action-command pair to the remote electronic device, the first command to cause performance of the first device action associated with the device action-command pair.

13. The method of claim 12 , comprising:

maintaining, for each device action-command pair of the first plurality of device action-command pairs, one or more corresponding keywords; and

identifying the context of the voice-based query based on the one or more keywords associated with the device action-command pair identified by the natural language processor component.

14. The method of claim 12 , wherein the first identifier includes a device model identifier (ID) indicative of a device model of the first plurality of remote electronic devices and the first plurality of device action-command pairs are specific to the device model.

15. The method of claim 14 comprising:

maintaining a description of the first plurality of remote electronic devices associated with the device model; and

identifying an attribute of the context of the voice-based query based on the description of the first plurality of remote electronic devices associated with device model.

16. The method of claim 12 , wherein the first identifier includes an identifier associated with an application installed on the first plurality of remote electronic devices and the first plurality of device action-command pairs are specific to the application.

17. The method of claim 16 comprising:

maintaining a description of the application installed on the first plurality of remote electronic devices; and

identifying an attribute of the context of the voice-based query based on the description of the application installed on the first plurality of remote electronic devices.

18. The method of claim 12 comprising:

identifying one or more parameter values of the first command associated with the device action-command pair; and

identifying an attribute of the context of the voice-based query based on the one or more parameter values of the first command associated with the device action-command pair.

19. A data processing system to provide content responsive to voice-based interactions, comprising:

a memory to store (i) first application action data including a first plurality of application action-command pairs supported by a first application executing on a plurality of remote electronic devices and defined by a provider of the first application, and (ii) second application action data including a second plurality of application action-command pairs supported by a second application executing on the plurality of remote electronic devices and defined by a provider of the second application, each application action-command pair including a respective application action of a plurality of application actions and a respective application executable command of a plurality of application executable commands to trigger performance of the respective application action;

a customization component to maintain a first mapping between a first identifier and the first application action data, and maintain a second mapping between a second identifier and the second application action data;

a communications interface to receive, from a remote electronic device of the plurality of remote electronic devices executing the first application, an audio signal and the first identifier, the audio signal obtained by the first application executing on the remote electronic device responsive to a voice-based query;

the customization component to identify, responsive to receipt of the audio signal and the first identifier, the first application action data using the first mapping between the first identifier and the first application action data;

a natural language processor component to identify, responsive to identifying the first application action data and using content associated with the audio signal, an application action-command pair of the first plurality of application action-command pairs in the first application action data, the application action-command pair including a first application action and a first command of the first application;

the device action customization component to identify a context of the voice-based query based on the first application action or the first command;

a content selector component to select, based on the context of the voice-based query, a third-party content item for presentation by the first application on the remote electronic device; and

the communications interface to transmit the third-party content item and the first command associated with the application action-command pair to the remote electronic device, the first command to cause performance of the first application action by the first application.