Multi-Device Voice Wakeup Selection Using Room-Aware Device Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a multi-device environment, unintended devices may wake up in response to a user's utterance, leading to overlapping calculations for voice recognition and delayed operation execution, and existing methods require explicit device specification in the utterance, inconveniencing the user.
Innovation Solution
An electronic device with a device detector, intelligence device resolver, and device selector that identifies and selects an appropriate device for operation based on user utterance, room information, and device characteristics, including installed applications and restrictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all devices wake up to recognize user utterance in multi-device environment, then the intended device can be identified, but overlapping calculations occur and response speed decreases
Solution Approach 1:
The system performs preliminary actions by having devices register their capabilities, locations, and characteristics in advance. When a user utterance occurs, the server can quickly match the utterance against pre-registered device information without requiring all devices to perform full wake-up and recognition calculations, thus reducing response time while maintaining accurate device selection
Solution Approach 2:
The patent extracts the voice recognition and natural language processing functions from individual devices and centralizes them on a server. Only the device nearest to the user needs to wake up and transmit the utterance to the server, which then identifies the appropriate target device. This extraction eliminates overlapping calculations across multiple devices while maintaining reliable device selection
2Reliability
If user explicitly specifies device in utterance, then operation can be executed on correct device, but user convenience decreases
Solution Approach 1:
The system enables devices to self-identify and self-select based on their pre-registered characteristics, capabilities, and location information. When the server receives a user utterance, it automatically determines which device should execute the operation by comparing the utterance intent with device profiles, eliminating the need for users to manually specify devices while ensuring accurate operation execution
Solution Approach 2:
The server acts as an intermediary between the user's utterance and the target device. It receives the utterance, performs natural language processing to understand user intent, matches the intent with appropriate devices based on pre-registered information, and routes the command to the correct device. This intermediary role eliminates the need for explicit device specification by users while maintaining high execution accuracy
Data Source
AI summary
An electronic device is provided. The electronic device includes a device detector, an intelligence device resolver (IDR), and a device selector. The device detector may receive user utterance information and identification information of multi-device wakeup (MDW) devices participating in MDW contention from a first electronic device selected in the MDW contention. The IDR may identify room information for locations of the MDW devices, based on the identification information of the MDW devices, and acquire device information of the MDW devices and devices located in an equal space to the MDW devices. The device selector may execute a command according to a user utterance, based on the device information of the MDW devices and the devices located in the equal space to the MDW devices.