Offline Voice Action Persistence in Smart Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-based user interfaces in devices like mobile phones and automotive systems face challenges with continuous online connectivity and latency issues, limiting their functionality when offline, as they rely on client-server architectures that require constant internet connection for processing voice inputs.
Innovation Solution
Implementing a method to locally persist data for selectively offline capable voice actions in voice-enabled devices, allowing these actions to be completed after online connectivity is restored, by performing local processing and storing data for later synchronization with online services when the device goes offline.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a client-server architecture is used for voice processing, then speech recognition and semantic analysis functionality can be enhanced, but the device requires continuous online connectivity and experiences increased latency
Solution Approach 1:
The patent segments voice processing functionality into offline-capable components (speech-to-text conversion, basic semantic analysis) that can operate independently without continuous online connectivity, while still allowing optional synchronization with online services for enhanced capabilities
Solution Approach 2:
The system performs preliminary voice processing actions offline using locally stored models and data, enabling voice commands to be executed immediately without waiting for online service responses, thus reducing latency while maintaining functionality
2Adaptability or versatility
If a client-server architecture is used for voice processing, then complex speech recognition and semantic analysis can be implemented, but the device becomes dependent on continuous online connectivity
Solution Approach 1:
The patent implements local quality by storing speech-to-text models, semantic analysis data, and voice processing algorithms locally on the device, enabling complex speech recognition and semantic analysis to function offline without dependency on continuous online connectivity
Solution Approach 2:
The system uses locally stored speech-to-text models and semantic analysis databases as intermediaries between the microphone and online services, enabling voice processing to occur offline while still allowing optional synchronization with online services for enhanced adaptability
3Loss of time
If offline processing is implemented, then latency is reduced and offline functionality is enabled, but computing resource requirements increase the device's power consumption
Solution Approach 1:
The patent applies partial action by implementing offline processing only for essential voice functions (speech-to-text conversion and basic semantic analysis) while allowing optional online synchronization for non-critical enhancements, thereby reducing power consumption compared to full offline processing while still achieving lower latency than complete online processing
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Data associated with a selectively offline capable voice action is locally persisted in a voice-enabled electronic device whenever such an action cannot be competed locally due to the device being offline to enable the action to later be completed after online connectivity has been restored. Synchronization with an online service and/or another electronic device, and/or retrieval of context sensitive data from an online service may be performed after online connectivity has been restored to enable the voice action to thereafter be completed.