Customizable Wake-Up Voice Commands for Smart Home Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current voice-controlled devices require users to explicitly enable voice commands, which can impede user experience and are inefficient, as they must be constantly ready to receive commands or use rigid non-voice interactions.

Innovation Solution

Implementing a customizable wake-up utterance system where users can select personalized words or phrases to trigger device activation, using a command hub with modules for wake-up detection, speech recognition, intent recognition, and command logic to interpret and execute voice commands, allowing devices to remain in a low power mode until an authorized wake-up utterance is detected.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the device is constantly ready to receive voice commands, then the user can issue commands immediately, but the device consumes excessive energy

Engineering Contradiction:
ImproveVoice command responsivenessVSAvoidDevice power consumption
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts its operational state based on incoming signals. The device transitions from a low-power state to an active voice command processing state only when a wake-up utterance is detected, optimizing the balance between responsiveness and energy consumption

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary detection of wake-up utterances before fully activating voice command processing. This preliminary action allows the device to remain in low-power mode while still being able to detect and respond to activation signals efficiently

Inventive Principle:
Principle #10Preliminary action

2Use of energy by moving object

If the device uses rigid non-voice interaction to enable voice commands, then the device can be activated on demand, but the user experience is impeded

Engineering Contradiction:
ImproveDevice power efficiencyVSAvoidUser interaction seamless
Core Design Contradiction:
Use of energy by moving objectVSEase of operation

Solution Approach 1:

The patent replaces mechanical button-pressing or touchscreen clicking with acoustic signal detection. The wake-up utterance detection system uses audio processing to trigger device activation, eliminating the need for physical interaction and creating a more seamless user experience

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables itself through voice-based wake-up utterances without requiring external activation. The device autonomously transitions from low-power mode to active state when it detects its designated wake-up phrase, making the activation process self-service and more natural

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If the device allows customizable wake-up utterances, then user personalization is improved, but device complexity increases

Engineering Contradiction:
ImproveWake-up command customizationVSAvoidConfiguration system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system allows users to programmatically configure custom wake-up utterances through application programming interfaces. This self-service approach enables users to personalize wake-up commands without requiring complex manual configuration interfaces or technical assistance

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent introduces an intermediary configuration layer that allows third-party applications to define and register custom wake-up utterances. This intermediary approach simplifies the core system by offloading customization complexity to an external configuration mechanism while maintaining flexibility

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3619707B1Customizable wake-up voice commands
Publication Date: 2024.02.21 MIDEA GROUP CO LTD
  • EP3619707B1 patent drawingFigure 1
  • EP3619707B1 patent drawingFigure 2
  • EP3619707B1 patent drawingFigure 3

AI summary

A voice command module is used to execute voice commands in a residential environment that contains a plurality of home devices. The voice command module includes a speech recognition module and command logic. The speech recognition module receives utterances from users and converts the utterances to commands from a vocabulary of predetermined commands, which includes a customization command to define a new wake-up utterance as corresponding to a wake-up command. The command logic executes the commands. When the customization command is received, the command logic changes the voice command module so that it now executes the wake-up command upon detection of the new wake-up utterance.