Virtual Assistant Handoff via Replanner Component
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems face challenges in seamlessly transitioning between different virtual assistants and managing command processing subsystems, particularly in determining the appropriate assistant to handle user commands and maintaining user experience consistency during handoffs.
Innovation Solution
The implementation of a replanner component that generates plan data for orchestrating handoffs between command processing subsystems, including user experience operations and command processing operations, to ensure smooth transitions and accurate execution of user commands, while utilizing assistant metadata to select appropriate handoff types and templates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple command processing subsystems are used to provide different virtual assistant experiences, then user choice and functionality are improved, but system complexity and coordination difficulty increase
Solution Approach 1:
The handoff manager acts as an intermediary component that coordinates between multiple command processing subsystems. It receives indications from one CPS, determines appropriate handoff types, and manages the transition to another CPS, thereby reducing the direct coordination complexity between subsystems while enabling versatile assistant selection.
Solution Approach 2:
The system segments the virtual assistant functionality into separate command processing subsystems, each handling specific assistant experiences. The handoff manager further segments the coordination logic into distinct handoff types (assistant-specific, user-preferred, load-based), making the complex coordination manageable through structured segmentation.
2Reliability
If handoffs between command processing subsystems are implemented, then user experience consistency is improved, but transition smoothness and coordination overhead present challenges
Solution Approach 1:
The handoff manager pre-determines handoff types based on assistant metadata and current system state before actual handoff execution. By preparing handoff parameters and selecting appropriate handoff types in advance, the system reduces transition time while maintaining consistent user experience across assistant switches.
3Measurement precision
If assistant metadata is used to select handoff types and templates, then handoff accuracy is improved, but data management complexity increases
Solution Approach 1:
The assistant metadata structure serves multiple functions: it stores assistant identifiers, defines handoff type preferences, specifies template selections, and provides load information. This universal data structure reduces the need for separate management systems for each handoff parameter, thereby improving handoff accuracy without proportionally increasing data management complexity.
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.” Different assistants may be available for use with a particular voice-controlled device based on time, location, the particular user, etc. In some situations, language processing may be improved by leveraging data such as intent data, grammars, lexicons, entities, etc., associated with assistants available for use with the particular voice-controlled device.