AI Device Wake-Up Selection via Speech Quality Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In a home environment with multiple artificial intelligence devices, users face difficulty in selecting the intended device to activate using a wake-up command due to simultaneous activation of multiple devices in response to the command.

Innovation Solution

An artificial intelligence device compares the speech quality of the wake-up command with external devices and selects the device with better quality, and also determines if the command volume is within an appropriate range to prevent unnecessary activation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple artificial intelligence devices are deployed in a home environment, then the coverage and availability of speech recognition services are improved, but it becomes difficult for users to select the intended device to activate

Engineering Contradiction:
Improvedevice availabilityVSAvoiddevice selection
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent applies local quality by making each device's wake-up command recognition capability location-specific. Devices evaluate speech quality metrics (volume, signal-to-noise ratio, acoustic environment) specific to their local position and compare these metrics to determine which device should be activated. This resolves the contradiction by maintaining high availability through multiple devices while enabling clear device selection through localized speech quality evaluation.

Inventive Principle:
Principle #3Local quality

2Speed

If all artificial intelligence devices activate in response to a wake-up command, then the responsiveness of the system is improved, but user confusion increases and the intended device cannot be identified

Engineering Contradiction:
Improveresponse speedVSAvoiddevice identification information
Core Design Contradiction:
SpeedVSLoss of information

Solution Approach 1:

The patent applies preliminary action by having devices evaluate speech quality metrics and determine activation eligibility before actually activating. Devices perform preliminary assessments of volume, signal-to-noise ratio, and acoustic environment, then use this information to select the single most appropriate device for activation. This resolves the contradiction by maintaining fast response through pre-evaluation while preventing confusion through predetermined selection criteria.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If speech quality evaluation is implemented to select the activated device, then device selection accuracy is improved, but the complexity of the system increases

Engineering Contradiction:
Improvedevice selection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by evaluating multiple speech quality parameters (volume, signal-to-noise ratio, acoustic environment characteristics) and using these parameter comparisons to determine device activation. Rather than implementing a complex centralized selection system, each device independently evaluates these parameters and selects itself based on having the most favorable speech quality metrics. This resolves the contradiction by achieving high selection accuracy through parameter evaluation while maintaining relatively simple device-level implementation.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3716266B1Artificial intelligence device and method of operating artificial intelligence device
Publication Date: 2023.10.25 LG ELECTRONICS INC
  • EP3716266B1 patent drawingFigure 1
  • EP3716266B1 patent drawingFigure 2~3
  • EP3716266B1 patent drawingFigure 4

AI summary

An artificial intelligence device includes a microphone configured to receive a speech command, a speaker, a communication unit configured to perform communication with an external artificial intelligence device, and a processor configured to receive a wake-up command through the microphone, acquire a first speech quality level of the received wake-up command, receive a second speech quality level of the wake-up command input to the external artificial intelligence device from the external artificial intelligence device through the communication unit, output a notification indicating that the artificial intelligence device is selected as an object to be controlled through the speaker, when the first speech quality level is larger than the second speech quality level, receive an operation command through the microphone, acquire an intention of the received operation command and transmit the operation command to an external artificial intelligence device which will perform operation corresponding to the operation command according to the acquired intention through the communication unit.