Orientation-Based Voice Assistant Switching for Privacy Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users are apprehensive about sending their voice data to cloud-based voice assistant services for privacy reasons, while cloud-based VASes offer more capabilities than local natural language units.
Innovation Solution
Network microphone devices (NMDs) toggle voice input processing between cloud-based VAS and local NLU based on physical orientation, enabling privacy protection by disabling cloud-based processing when the device is oriented in a certain way.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voice input processing is done via cloud-based VAS, then capabilities and functionality are improved, but privacy and security are worsened
Solution Approach 1:
The system dynamically switches between cloud-based VAS and local NLU processing modes based on device orientation detected by the sensor. When the device is in a first orientation, cloud VAS is enabled for full functionality. When in a second orientation, local NLU processing is activated for privacy protection. This dynamic switching resolves the contradiction by allowing the system to adapt its processing location based on user needs.
Solution Approach 2:
The system changes the processing parameter (cloud vs. local) based on the physical orientation parameter of the device. By detecting orientation changes through sensors, the system transitions between different processing modes, enabling users to control whether voice data is sent to cloud or processed locally based on the device's physical state.
2Object-affected harmful factors
If voice input processing is done via local NLU, then privacy is improved, but capabilities and functionality are worsened
Solution Approach 1:
The system provides dynamic access to different processing capabilities based on device orientation. Users can orient the device to switch between privacy-focused local processing and capability-rich cloud processing, ensuring that both privacy and functionality can be achieved depending on the situation.
Solution Approach 2:
The system combines both cloud-based VAS and local NLU processing capabilities in a single device, allowing it to perform multiple functions depending on orientation. This multi-functionality enables the device to provide both privacy protection and advanced capabilities without requiring separate devices.
3Ease of operation
If device orientation is used to toggle VAS mode, then privacy control is improved, but device complexity is worsened
Solution Approach 1:
The system uses the device's own sensor to automatically detect orientation and switch processing modes without requiring user intervention. The device serves itself by interpreting its physical orientation to determine the appropriate processing mode, simplifying the user experience while managing the complexity internally.
Solution Approach 2:
The system replaces complex software-based switching mechanisms with a simpler sensor-based orientation detection system. By using physical orientation sensors, the system achieves easy privacy control through a straightforward mechanical/physical state rather than complex software configuration.
Data Source
AI summary
As noted above, example techniques relate to toggling a cloud-based VAS between enabled and disabled modes. An example implementation involves a NMD detecting that the housing is in a first orientation and enabling a first mode. Enabling the first mode includes disabling voice input processing via a cloud-based VAS and enabling local voice input processing. In the first mode, the NMD captures sound data associated with a first voice input and detects, via a local natural language unit, that the first voice input comprises sound data matching one or more keywords. The NMD determines an intent of the first voice input and performs a first command according to the determined intent. The NMD may detect that the housing is in a second orientation and enables the second mode. Enabling the second mode includes enabling voice input processing via the cloud-based VAS.