Electronic Device Voice Engine Selection by Power and Network State

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic devices face inefficiencies in voice recognition due to power-off or network disconnection states, and the inappropriate selection of voice recognition engines for certain functions, such as power or channel control, leading to suboptimal performance.

Innovation Solution

An electronic device that selects a voice recognition engine based on correlations between device states and engine capabilities, using on-device and server engines, to optimize voice recognition efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a server voice recognition engine is selected for all voice recognition tasks, then voice recognition accuracy is improved, but response speed and processing efficiency deteriorate when the device is in power-off or network disconnection states

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidvoice recognition availability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The voice recognition system is segmented into two independent engines: an on-device voice recognition engine for local processing and a server voice recognition engine for cloud-based processing. The processor selectively activates the appropriate engine based on device state (power state, network state), ensuring both accuracy and availability across different operating conditions

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes the operational parameters of voice recognition by switching between two different engines based on device state parameters. When the device is in power-off or network disconnection states, the on-device engine is activated; otherwise, the server engine is used, optimizing performance according to current system conditions

Inventive Principle:
Principle #35Parameter changes

2Speed

If an on-device voice recognition engine is used for simple commands, then processing speed is improved, but voice recognition accuracy deteriorates for complex intents

Engineering Contradiction:
Improveprocessing speedVSAvoidvoice recognition accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The system dynamically adjusts the voice recognition engine selection based on real-time device state and voice input characteristics. The processor evaluates both the simplicity of the command and the current device state to determine whether to use the on-device or server engine, optimizing the balance between speed and accuracy

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The processor acts as an intermediary that evaluates voice input and device state, then selects the appropriate voice recognition engine. This intermediary layer ensures that simple commands are processed quickly by the on-device engine while complex intents are routed to the more accurate server engine

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple voice recognition engines are maintained, then adaptability to different device states is improved, but device complexity increases

Engineering Contradiction:
Improveadaptability to device statesVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The on-device voice recognition engine is designed to handle multiple functions and different device states (power-off state, network disconnection state). This universal engine reduces the need for specialized engines for each state, simplifying the overall system architecture while maintaining adaptability

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

Solution Approach 2:

The on-device voice recognition engine provides self-service capabilities by handling voice recognition locally without requiring external server resources. This allows the device to independently process voice inputs in states where network connectivity or full system power is unavailable

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4227940B1Electronic device and method for controlling same
Publication Date: 2025.08.20 SAMSUNG ELECTRONICS CO LTD
  • EP4227940B1 patent drawingFigure 1
  • EP4227940B1 patent drawingFigure 2
  • EP4227940B1 patent drawingFigure 3

AI summary

An electronic device includes a processor configured to: receive a user voice input, identify a state of the electronic device corresponding to at least one item related to the electronic device, select a voice recognition engine, from among a plurality of voice recognition engines, based on the voice recognition engine having a highest correlation with the identified state from among correlations between the plurality of voice recognition engines and a plurality of states, and perform an operation corresponding to the user voice input based on the selected voice recognition engine.