Multi-Device Wake Word Routing by Confidence and App Authority
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining a device to process a user's utterance in a multi-device environment often select a device without considering the user's intent, leading to inefficient resource usage and potential privacy issues.
Innovation Solution
An electronic device determines the optimal device for processing an utterance based on confidence values, hardware information, and application information, ensuring that the selected device has the necessary authority to execute the action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional methods use intensity of input audio signal or distance to determine device selection, then device selection can be made简单地, but the selected device may not be the most appropriate for processing the user's intent
Solution Approach 1:
The patent changes the selection parameters from simple physical metrics (intensity, distance) to comprehensive device attributes including confidence values, hardware capabilities, and application information. This allows the system to select the most appropriate device based on both the user's intent and the device's ability to execute it.
Solution Approach 2:
The patent introduces an intermediary selection mechanism that receives information from multiple devices and determines the winner based on comprehensive criteria. This intermediary layer processes confidence values, hardware information, and application information to make an informed selection rather than relying on simple physical measurements.
2Loss of energy
If multiple devices process utterances without proper selection, then resource usage increases, but determining the optimal device requires complex evaluation criteria
Solution Approach 1:
The patent performs preliminary evaluation of device capabilities, confidence values, and application information before the actual utterance processing. By pre-assessing which device is most suitable based on their respective capabilities and the user's intent, the system avoids unnecessary processing on inappropriate devices, thus reducing resource consumption while managing complexity through structured evaluation.
Solution Approach 2:
Each device provides information about its own capabilities, hardware status, and running applications to the selection mechanism. This self-service approach allows devices to autonomously contribute their suitability metrics without requiring external assessment, simplifying the overall system architecture while enabling intelligent selection.
3Device complexity
If device selection is made without considering application information, then selection process is simpler, but the selected device may lack necessary authority to execute the action
Solution Approach 1:
The patent adds application information as a critical selection parameter, evaluating which device has the necessary authority and capability to execute the user's intent. This includes checking running applications, device capabilities, and contextual suitability, ensuring that the selected device can actually perform the required action.
Data Source
AI summary
An electronic device and an utterance processing method of an electronic device are provided. The electronic device includes a processor and a memory configured to store instructions to be executed by the processor. The processor receives an utterance of a user received by a plurality of devices, a confidence value corresponding to a wakeup utterance calculated by the plurality of devices, hardware information of the plurality of devices, and application information of an application executed on the plurality of devices, determines an action for processing the utterance of the user, and determines a target device to perform the action from among the plurality of devices based on the confidence value, the hardware information, and the application information.