Home Appliance Voice Recognition via Server Offloading

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice recognition systems for home appliances face limitations in recognizing natural language voice commands due to resource constraints and high computational requirements, leading to inefficiencies and increased chances of false recognition.

Innovation Solution

A method utilizing a voice recognition server system that offloads natural language processing from individual home appliances, using a network of servers for voice command recognition and processing, allowing home appliances to receive voice inputs and perform actions without the need for manual remote control manipulation, with features like feedback operations and audible guidance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If voice recognition processing is performed using embedded modules in individual home appliances, then the system can operate autonomously, but the computational resources required for natural language recognition cannot be adequately provided

Engineering Contradiction:
Improveautonomous operationVSAvoidcomputational power
Core Design Contradiction:
Extent of automationVSPower

Solution Approach 1:

A voice recognition server system acts as an intermediary between the user and the home appliance. The server performs the computationally intensive natural language recognition processing, while the home appliance simply transmits voice data and receives control signals. This resolves the contradiction by externalizing the computational burden to a server with sufficient processing power while maintaining autonomous operation of the appliance.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If simple keyword recognition is used in home appliances, then system resources are conserved, but the ability to recognize various natural languages is limited

Engineering Contradiction:
Improvelanguage recognition capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The voice recognition server serves as an intermediary that handles the complex natural language processing. The home appliance itself remains simple, only needing to transmit voice data and execute received commands. This allows the system to support various natural languages without increasing the complexity of the individual appliance.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If voice recognition processing is centralized in a server system, then natural language recognition capability is improved, but the system requires network communication infrastructure

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidsystem architecture complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system is segmented into distinct functional components: the home appliance handles voice input and command execution, while the voice recognition server handles natural language processing. This segmentation allows each component to be optimized for its specific function, improving recognition accuracy while keeping the overall system architecture manageable through clear separation of concerns.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3413304B1Method for operating home appliance
Publication Date: 2022.08.31 LG ELECTRONICS INC
  • EP3413304B1 patent drawingFigure 1
  • EP3413304B1 patent drawingFigure 2
  • EP3413304B1 patent drawingFigure 3a

AI summary

Disclosed is a method for operating a home appliance, including: activating a voice recognition function; entering a wake-up signal standby mode for receiving a wake-up voice signal including a preset call word; receiving the wake-up voice signal via an audio input unit including one or more microphones; entering a command standby mode for receiving a user's voice command within a preset period of time; receiving a voice command via the audio input unit; and transmitting, to a voice recognition server system, voice data including a voice command received for the preset period of time and the call word. In doing so, it is possible to recognize a user's voice command more accurately.