Multi-VAS Voice Routing for Unfulfilled Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice assistant services (VAS) may be unavailable, in do-not-disturb mode, busy, or lack necessary skills, leading to unfulfilled voice commands and queries, especially in multi-VAS environments where devices are not configured to operate within a single ecosystem.
Innovation Solution
A system and method for managing multiple VASs by identifying context, assessing skills, seeking user permission, and classifying voice inputs to assign tasks to available VASs, enabling collaboration and skill configuration when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a primary voice assistant service is unavailable, in do-not-disturb mode, or lacks necessary skills, then voice commands cannot be fulfilled, but assigning to a secondary VAS may introduce delays or require additional user permission steps
Solution Approach 1:
The system performs preliminary assessment of the primary VAS's availability, mode, and skill set before voice command execution. By checking these conditions in advance and having a pre-configured secondary VAS ready, the system can quickly switch without significant delay when the primary VAS is unavailable.
Solution Approach 2:
The system introduces an intermediary assignment mechanism that mediates between the primary and secondary VASs. This intermediary layer evaluates the primary VAS's status and automatically routes commands to the appropriate service, minimizing user-perceived delay while ensuring reliable command fulfillment.
2Reliability
If the system assigns voice commands to a secondary VAS when the primary is unavailable, then command fulfillment is maintained, but system complexity increases due to multiple VAS management
Solution Approach 1:
The system introduces an intermediary assignment mechanism that mediates between the primary and secondary VASs. This intermediary layer evaluates the primary VAS's status and automatically routes commands to the appropriate service, minimizing user-perceived delay while ensuring reliable command fulfillment.
Solution Approach 2:
The system treats multiple voice assistant services with a unified evaluation framework, assessing them on common criteria such as availability, mode, and skill set. This homogeneous approach simplifies the management of multiple heterogeneous VASs by applying consistent selection rules across all services.
3Ease of operation
If the system seeks user permission before assigning skills to secondary VAS, then user control is maintained, but the process becomes more complex and time-consuming
Solution Approach 1:
The system performs preliminary assessment of the primary VAS's availability, mode, and skill set before voice command execution. By checking these conditions in advance and having a pre-configured secondary VAS ready, the system can quickly switch without significant delay when the primary VAS is unavailable.
Solution Approach 2:
The system implements a feedback mechanism where the secondary VAS communicates its skill availability and readiness to the assignment system. This feedback loop allows the system to make informed decisions about skill assignment without requiring complex user configuration, maintaining user control through transparent information provision.
Data Source
AI summary
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.