Voice Interaction Dispatch Logic for Application Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition systems face challenges in determining which software application should handle a user's voice interaction when multiple applications are available, leading to limited flexibility and increased computational overhead, as well as user micro-management.
Innovation Solution
An open framework for dispatch logic that allows voice-interaction enabled applications to self-identify and determine their ability to respond to user requests, decentralizing decision-making and enabling sequential querying until an appropriate application is found.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a primary ASR program centrally determines which application handles voice interactions, then decision-making is centralized and consistent, but flexibility is limited and computational overhead increases
Solution Approach 1:
The patent segments the centralized decision-making process into distributed components. Instead of one primary ASR program determining application selection, multiple ASR programs independently evaluate and select applications. This segmentation reduces the computational burden on any single program and increases system flexibility by allowing parallel processing and diverse selection strategies across different ASR programs.
Solution Approach 2:
The patent enables ASR programs to self-determine application selection without requiring a central controller. Each ASR program autonomously evaluates voice interactions and selects appropriate applications based on its own capabilities and the current context. This self-service approach eliminates the need for complex centralized coordination and reduces overall computational overhead.
2Adaptability or versatility
If multiple ASR programs are used to handle voice interactions, then flexibility and application selection capability improve, but system complexity increases
Solution Approach 1:
The patent merges the application selection functionality into the existing ASR programs themselves, rather than adding a separate selection layer. Each ASR program is enhanced with the capability to directly select applications, combining speech recognition and application selection into unified components. This merging approach increases application selection capability while avoiding the complexity of additional system layers.
3Ease of operation
If user intervention is required to select applications for voice interactions, then precise control is achieved, but ease of operation decreases
Solution Approach 1:
The patent implements self-service by enabling ASR programs to automatically select applications without user intervention. The system autonomously evaluates the voice interaction, determines the appropriate application, and routes the interaction accordingly. This automation significantly improves ease of operation while maintaining intelligent decision-making capabilities.
Solution Approach 2:
The patent incorporates feedback mechanisms where ASR programs continuously learn from user interactions and application selection outcomes. The system monitors which applications successfully handle voice interactions and uses this feedback to improve future selection decisions. This feedback loop enables the system to become increasingly accurate and adaptive without requiring user intervention.
Data Source
AI summary
An open framework for computing devices to dispatch voice-based interactions to supporting applications. Applications are selected on a trial-and-error basis to find an application able to handle the voice interaction. Dispatching to the applications may be performed without a determination of meaning conveyed in the interaction, with meaning determined by the individual applications. Once an application acts upon a voice interaction, that application may be given first-right-of-refusal for subsequent voice interactions.