Systems and methods for managing multiple voice assistant services based on voice input
Systems and methods are described for assigning a voice assistant service (VAS) from multiple VASs, based on a voice input. The system generally comprises a processor that is configured to process at least one voice input, e.g., with a wake word, and assign at least one VAS to output a response based on the voice input. Some embodiments support the skill or skills of a secondary VAS when the primary VAS is unavailable or when the primary VAS does not possess the required skill. The system may evaluate the skills required to process a user request based on the context and/or intent. The system may distribute data related to voice input and context and/or intent among various VASs to complete a task. Furthermore, the system may classify voice input as generic voice input or target VAS-specific voice input, e.g., by utilizing a trained model.
1. A method of assigning a voice assistant service (VAS) for a voice command, the method comprising:
receiving, by a device having at least a first VAS and a second VAS, a voice input comprising a voice input context;
determining whether the voice input context requires a VAS skill to access third-party data related to the voice input context;
in response to determining that the voice input context requires the VAS skill to access the third-party data, accessing authorization data for each of a plurality of skills for the first VAS;
determining whether the authorization data describing for each of the plurality of skills for the first VAS indicates the first VAS is authorized to access the third-party data; and
based at least in part on determining the authorization data for each of the plurality of skills for the first VAS indicates the first VAS is not authorized to access the third-party data:
determining the second VAS with a plurality of skills has the VAS skill to access the third-party data; and
causing the second VAS to respond to the voice input using the VAS skill to access the third-party data.
2. The method of claim 1 , further comprising, determining whether the authorization data for each of the plurality of skills for the first VAS indicates if the first VAS is authorized to access the third-party data by determining whether the first VAS is unavailable.
3. The method of claim 2 , wherein unavailable comprises any of the following: busy, powered off, muted, disconnected, in a sleep mode, or in a do-not-disturb mode.
4. The method of claim 1 , further comprising: determining whether the authorization data for each of the plurality of skills for the first VAS indicates if the first VAS is authorized to access the third-party data by determining whether the first VAS is compatible with the VAS skill.
5. The method of claim 1 , wherein the causing the second VAS to respond to the voice input comprises requesting permission to enable the VAS skill.
6. The method of claim 1 , wherein the determining the second VAS further comprises determining whether the VAS skill is enabled on the second VAS; and
wherein the causing the second VAS to respond to the voice input comprises requesting permission to enable the VAS skill in response to determining the VAS skill is not enabled on the second VAS.
7. The method of claim 1 , wherein the determining whether the voice input context requires the VAS skill comprises determining whether the voice input context or the VAS skill is urgent; and
wherein determining whether the authorization data for each of the plurality of skills for the first VAS indicates the first VAS is authorized to access the third-party data comprises overriding a determination that the first VAS is not available.
8. The method of claim 1 , wherein the determining whether the voice input context requires the VAS skill comprises classifying the voice input context as a generic context or a VAS-specific context.
9. The method of claim 8 , wherein the classifying the voice input context comprises using a trained machine learning model to classify the voice input context as the generic context or the VAS-specific context.
10. The method of claim 8 , wherein the classifying the voice input context comprises:
processing the voice input context as a plurality of segments;
determining whether the plurality of segments requires a joint command execution or in a partial command execution;
implementing a parallel processing of the plurality of segments in response to determining that the plurality of segments requires the joint command execution; and
implementing a sequential processing of the plurality of segments in response to determining that the plurality of segments requires the partial command execution.
11. A system for assigning a voice assistant service (VAS) for a voice command, the system comprising:
memory;
input/output circuitry configured to receive a voice input comprising a voice input context;
processing circuitry configured to:
determine whether the voice input context requires a VAS skill to access third-party data related to the voice input context;
in response to determining that the voice input context requires the VAS skill to access the third-party data, access authorization data for each of a plurality of skills for a first VAS;
determine whether the authorization data for each of the plurality of skills for the first VAS indicates the first VAS is authorized to access the third-party data; and
based at least in part on determining the authorization data for each of the plurality of skills for the first VAS indicates the first VAS is not authorized to access the third-party data:
determine a second VAS with a plurality of skills has the VAS skill to access the third-party data; and
cause the second VAS to respond to the voice input using the VAS skill to access the third-party data.
12. The system of claim 11 , wherein the processing circuitry is further configured to determine whether the authorization data for each of the plurality of skills for the first VAS indicates if the first VAS is byauthorized to access the third-party data by determining whether the first VAS is unavailable.
13. The system of claim 12 , wherein unavailable comprises any of the following: busy, powered off, muted, disconnected, in a sleep mode, or in a do-not-disturb mode.
14. The system of claim 11 , wherein the processing circuitry is further configured to determine whether the authorization data for each of the plurality of skills for the first VAS indicates if the first VAS is authorized to access the third-party data by determining whether the first VAS is compatible with the VAS skill.
15. The system of claim 11 , wherein the processing circuitry is further configured to cause the second VAS to respond to the voice input by requesting permission to enable the VAS skill.
16. The system of claim 11 , wherein the processing circuitry is further configured to determine a second VAS by determining whether the VAS skill is enabled on the second VAS; and
wherein the processing circuitry is further configured to cause the second VAS to respond to the voice input by requesting permission to enable the VAS skill in response to determining the VAS skill is not enabled on the second VAS.
17. The system of claim 11 , wherein the processing circuitry is further configured to determine whether the voice input context requires the VAS skill by determining whether the voice input context or the VAS skill is urgent; and
wherein the processing circuitry is further configured to determine whether the authorization data for each of the plurality of skills for the first VAS indicates the first VAS is authorized to access the third-party data by overriding a determination that the first VAS is not available.
18. The system of claim 11 , wherein the processing circuitry is further configured to determine whether the voice input context requires the VAS skill by classifying the voice input context as a generic context or a VAS-specific context.
19. The system of claim 18 , wherein the processing circuitry is further configured to classify the voice input context by:
processing the voice input context as a plurality of segments;
determining whether the plurality of segments requires a joint command execution or in a partial command execution;
implementing a parallel processing of the plurality of segments in response to determining that the plurality of segments requires the joint command execution; and
implementing a sequential processing of the plurality of segments in response to determining that the plurality of segments requires the partial command execution.
20. A method comprising:
receiving, by a device having at least a first voice assistant service (VAS) and a second VAS, a voice input comprising a voice input context;
determining whether the voice input context requires a VAS skill to access third-party data related to the voice input context;
in response to determining that the voice input context requires the VAS skill to access the third-party data, accessing authorization data for each of one or more skills for the first VAS;
determining whether the authorization data for each of the one or more skills for the first VAS indicates the first VAS is authorized to access the third-party data; and
based at least in part on determining the authorization data for each of the one or more skills for the first VAS indicates the first VAS is not authorized to access the third-party data:
determining the second VAS has the VAS skill to access the third-party data; and
causing the second VAS to respond to the voice input using the VAS skill to access the third-party data.