Virtual Assistant Triggering via Conditional Audio Sampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual assistant systems lack efficient techniques for triggering virtual assistants across various usage scenarios, especially on battery-powered portable electronic devices where power conservation is crucial.
Innovation Solution
A method for triggering a virtual assistant on an electronic device with a display, microphone, and input device, involving receiving user input meeting a predetermined condition, sampling audio input, determining if it comprises a spoken trigger, and triggering a virtual assistant session accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If continuous audio sampling is performed to enable virtual assistant triggering, then responsiveness to user commands is improved, but battery power consumption increases
Solution Approach 1:
The system implements periodic audio sampling instead of continuous sampling, activating the microphone and processing audio input only at specific intervals or upon detecting certain conditions (such as display on state or software events). This periodic approach maintains the ability to respond to user commands while significantly reducing battery power consumption compared to continuous monitoring.
2Loss of time
If audio sampling is performed frequently to detect spoken triggers quickly, then trigger detection speed is improved, but energy consumption increases
Solution Approach 1:
The system performs preliminary checks before initiating full audio sampling, such as checking the display on state or detecting specific software events. This preliminary action allows the system to prepare for potential trigger detection without continuously consuming energy, reducing both the trigger detection delay and energy consumption by only activating full sampling when conditions are appropriate.
3Adaptability or versatility
If the system monitors multiple usage scenarios for virtual assistant activation, then versatility of triggering is improved, but system complexity increases
Solution Approach 1:
The system implements a universal triggering mechanism that works across multiple usage scenarios through a single integrated approach. By checking common conditions (display on state, software events) and using a unified audio sampling process, the system achieves versatility in triggering the virtual assistant without requiring separate complex monitoring systems for each scenario, thus maintaining low system complexity while supporting multiple usage contexts.
Data Source
AI summary
At an electronic device with a display, a microphone, and an input device: while the display is on, receiving user input via the input device, the user input meeting a predetermined condition; in accordance with receiving the user input meeting the predetermined condition, sampling audio input received via the microphone; determining whether the audio input comprises a spoken trigger; and in accordance with a determination that audio input comprises the spoken trigger, triggering a virtual assistant session.


