Server Speech Command Reactivation via Word Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users of home appliances face inconvenience when controlling them using speech recognition technology, as they need to repeatedly reactivate the speech command receiving function after each command, and there is no automatic reactivation mechanism.

Innovation Solution

A server system that automatically reactivates the speech command receiving function of home appliances by recognizing specific words in user speech input and transmitting response signals with control commands to maintain continuous functionality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speech recognition technology is used to control home appliances, then user convenience is improved, but the user must repeatedly reactivate the speech command receiving function after each command

Engineering Contradiction:
Improveuser convenienceVSAvoidtime to reactivate speech command function
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The server performs preliminary analysis of the user's speech to determine if additional commands are likely to follow. Based on this preliminary assessment, the server proactively maintains the speech command receiving function active without requiring the user to reactivate it, thus preparing the system in advance for potential continued interaction.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The server analyzes the user's speech input and provides feedback by determining whether to maintain the speech command receiving function active. This feedback mechanism allows the system to adapt its operational state based on the characteristics of the user's input, creating a closed-loop control system that automatically adjusts to user needs.

Inventive Principle:
Principle #23Feedback

2Productivity

If the speech command receiving function is terminated after each command, then system resource usage is reduced, but user interaction becomes inefficient

Engineering Contradiction:
Improvecommand execution efficiencyVSAvoidinteraction convenience
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The speech command receiving function transitions from a static on/off state to a dynamic state that can be maintained active based on real-time analysis of user speech patterns. This dynamic adjustment allows the system to optimize between resource usage and interaction efficiency by adapting its operational state to the specific context of each user interaction.

Inventive Principle:
Principle #15Dynamics

3Speed

If the server maintains continuous speech listening, then response time is improved, but energy consumption increases

Engineering Contradiction:
Improvespeech response timeVSAvoidserver energy consumption
Core Design Contradiction:
SpeedVSUse of energy by moving object

Solution Approach 1:

Instead of continuous speech listening, the server implements periodic activation of the speech command receiving function based on analysis of user speech patterns. The function is maintained active during periods when additional commands are likely and deactivated when not needed, creating a periodic on/off pattern that balances response time requirements with energy conservation.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3923276B1Server and system including the same
Publication Date: 2025.04.16 LG ELECTRONICS INC
  • EP3923276B1 patent drawingFigure 1
  • EP3923276B1 patent drawingFigure 2
  • EP3923276B1 patent drawingFigure 3

AI summary

The present disclosure relates to a server and a system including the same. The server according to an embodiment of the present disclosure includes: a communicator configured to perform communication through a network; a storage configured to store data on at least one predetermined word; and a controller configured to: upon receiving an input signal, including data on speech, from a first electronic device through the communicator, determine whether a last part of the speech corresponds to any one of the at least one predetermined word; in response to there being a word corresponding to the last part of the speech among the at least one predetermined word, transmit a first response signal, including data on a response to the speech and data on at least one additional query, to the first electronic device through the communicator; and in response to there being no word corresponding to the last part of the speech among the at least one predetermined word, transmit a second response signal, including data on a response to the speech, to the first electronic device through the communicator. Various other embodiments are also possible.