Voice Control Terminal Auto-Wake Mechanism

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice control systems require users to manually activate and wake up the terminal before issuing voice commands, leading to increased operational complexity and inconvenience, especially when the terminal is turned off or in a sleeping state.

Innovation Solution

A method where the terminal continuously monitors user voice segments and sends an enable signal to the main voice system when a voice segment with an enable attribute is detected, allowing voice commands to be issued without prior activation, enabling continuous voice command functionality and preventing system unavailability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the terminal continuously monitors user voice segments and automatically enables the voice system, then the ease of operation is improved, but the energy consumption increases

Engineering Contradiction:
Improveease of operationVSAvoidenergy consumption
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The terminal performs preliminary voice monitoring and detection before the user actually needs to use the voice system. The system pre-enables the voice function by detecting wake-up keywords or specific voice patterns, so that when the user issues a voice command, the system is already ready to process it immediately, eliminating the need for manual activation and reducing the operational steps.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The voice monitoring system operates autonomously to detect when the user intends to use voice commands. The system self-enables the voice function based on detected voice patterns or keywords without requiring user intervention, and automatically manages the transition between monitoring and full voice processing modes, thereby simplifying user interaction while managing energy consumption through automated state transitions.

Inventive Principle:
Principle #25Self-service

2Speed

If the terminal enables the voice system immediately upon detection, then the response speed is improved, but the reliability deteriorates due to potential false triggering

Engineering Contradiction:
Improveresponse speedVSAvoidreliability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary detection of voice segments and analyzes them for specific characteristics (such as wake-up keywords, voice patterns, or contextual cues) before triggering the full voice system. This preliminary analysis stage acts as a filter to distinguish between intentional voice commands and background noise, reducing false triggering while maintaining fast response times when genuine commands are detected.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where the detected voice segments are analyzed and validated before system activation. The monitoring module provides feedback about the detected voice patterns to the control logic, which determines whether to enable the voice system based on confidence thresholds or pattern matching results, thereby improving reliability by confirming the intent before full system activation.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3157003B1Terminal control method and device, voice control device and terminal
Publication Date: 2018.10.31 ZTE CORP
  • EP3157003B1 patent drawingFigure 1
  • EP3157003B1 patent drawingFigure 2~3
  • EP3157003B1 patent drawingFigure 4

AI summary

A terminal control method and device, a voice control device and a terminal are provided in the present invention. The method comprises: monitoring user voices including at least one voice fraction when it is detected that a main voice system of the terminal is closed; determining whether the voice fraction provided with a starting-up property appears, and if yes, sending out a starting-up signal used for starting up the main voice system of the terminal, and storing the voice fractions being monitored after the voice fraction provided with the starting-up property; and sending out the stored voice fractions after it is detected that the main voice system of the terminal is successfully started up. By the implementation of the present invention, when the main voice system of the terminal is closed, the voice fractions are detected to judge out whether it is required to start up the main voice system of the terminal. If it is required, the starting-up signal is sent out, meanwhile, after the starting-up signal is sent out, the subsequent voice fractions are stored in parallel, so that the user can speak out voice instructions continuously, with no need for waiting for the starting-up of the main voice system of the terminal. Thereby the problem in the prior art that the operations of the voice control technology are complicated is solved.