Master Control Device Arbitrates Smart Speaker Wake-Up

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Multiple voice smart devices with the same wake-up word interfere with each other when activated, leading to poor user experiences due to simultaneous responses.

Innovation Solution

A master control device receives wake-up messages from smart devices, determining the target device to wake up based on sound characteristics, and sends a wake-up instruction to that device, ensuring only one device responds to user requests.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If multiple smart devices use the same wake-up word, then the user experience is improved by not needing to remember different wake-up words, but the devices interfere with each other and respond simultaneously causing poor user experience

Engineering Contradiction:
Improveease of useVSAvoidmutual interference
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The patent introduces a master control device as an intermediary between the smart devices and the user's voice command. When a wake-up word is detected, the master control device receives wake-up messages from multiple smart devices, determines the target device based on sound characteristics (such as volume intensity indicating distance), and sends a wake-up instruction only to that target device. This mediator approach resolves the conflict by allowing multiple devices to share the same wake-up word while preventing simultaneous responses through centralized arbitration.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If the user defines different wake-up words for each smart device, then mutual interference is avoided, but the user convenience deteriorates due to needing to remember multiple wake-up words

Engineering Contradiction:
Improvemutual interferenceVSAvoiduser convenience
Core Design Contradiction:
Object-affected harmful factorsVSEase of operation

Solution Approach 1:

The patent implements universality by allowing multiple smart devices to share the same wake-up word. Instead of requiring unique wake-up words for each device, the system enables a universal wake-up word to be used across all devices. The master control device then handles the differentiation by selecting the appropriate target device based on sound characteristics, thus providing multi-functionality where one wake-up word serves multiple devices without causing interference.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Speed

If all smart devices respond to the wake-up word simultaneously, then the system is simple and responsive, but the user experience deteriorates due to mutual interference and confusion

Engineering Contradiction:
Improveresponse speedVSAvoidmutual interference
Core Design Contradiction:
SpeedVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by having the master control device determine the target smart device before actually waking it up. The system receives wake-up messages from multiple devices, uses sound characteristics to identify the closest device (the target), and then sends the wake-up instruction only to that determined target. This preliminary determination step prevents simultaneous responses while maintaining fast overall response time, as the selection process occurs in parallel with the wake-up preparation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11355107B2Voice smart device wake-up method, apparatus, device and storage medium
Publication Date: 2022.06.07 BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
  • US11355107B2 patent drawing
  • US11355107B2 patent drawing
  • US11355107B2 patent drawing

AI summary

Embodiments of the present disclosure provide a voice smart device wake-up method, apparatus, device and storage medium. The method includes: receiving, by a master control device, a wake-up message sent by each smart device, the wake-up message comprising at least sound characteristics information, determining, by the master control device, a target smart device to be woken up according to the sound characteristics information, and sending, by the master control device, a wake-up instruction to the target smart device to be woken up, to wake up the target smart device to be woken up for responding to a voice request from a user. In a case where a plurality of smart devices share a same wake-up word, only one most suitable smart device is waken up to respond to a voice request of the user each time.