Replanner Component for Virtual Assistant Command Handoff
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems face challenges in seamlessly transitioning user commands between different virtual assistants, particularly when a user invokes one assistant but the command is better handled by another, leading to issues in output coordination and user experience.
Innovation Solution
The implementation of a replanner component that generates plan data for handoffs between command processing subsystems, ensuring smooth transitions and accurate execution of user commands by selecting the appropriate assistant based on the intent and available skills, while providing verbal and non-verbal cues to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single virtual assistant handles all user commands, then the system structure is simple, but the system cannot seamlessly transition between assistants and lacks flexibility in command routing
Solution Approach 1:
The system divides the single assistant into multiple virtual assistants, each capable of handling specific commands or types of requests. The replanner component segments the command routing decision-making process, evaluating each command independently to determine the most appropriate assistant, thereby enabling flexible command routing while maintaining manageable system architecture through modular design
2Reliability
If the system automatically selects the best assistant for each command, then command execution reliability improves, but the complexity of determining and coordinating assistant selection increases
Solution Approach 1:
The replanner component performs preliminary evaluation of each user command before it is executed, analyzing the command characteristics and available assistants in advance to determine the optimal assistant selection. This preliminary action ensures reliable command execution by pre-determining the best match, while the systematic approach to evaluation reduces coordination complexity through structured decision-making protocols
3Ease of operation
If the system provides detailed feedback to users about assistant selection, then user experience and transparency improve, but the amount of information processing and communication overhead increases
Solution Approach 1:
The feedback mechanism provides localized information to users only when and where it is most beneficial. The replanner component determines the appropriate level and type of feedback based on the specific command and user context, delivering detailed explanations for assistant selection in cases where it enhances user understanding, while maintaining concise communication in routine situations to minimize overhead
Data Source
AI summary
A speech-processing system may provide access to multiple virtual assistants via one or more voice-controlled devices. Each assistant may leverage language processing and language generation features of the speech-processing system, while handling different commands and/or providing access to different back applications. Each assistant may be associated with its own voice and/or speech style, and thus be perceived as having a particular “personality.” In some situations, a user may invoke a first assistant, e.g., with a wakeword or button press, and provide a command that the speech-processing system may determine will be better handled by a second assistant. The speech-processing system may thus call on a component to generate plan data describing one or more operations for the speech-processing system to execute to handoff the command to the second assistant and provide the user with indications of which assistant will handle the command.