GUI Voice Control Real-Time Pattern Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional voice control systems for GUIs face challenges in achieving accurate and rapid voice recognition due to reliance on end point detection methods, which can lead to delayed responses and poor accuracy, especially when short pauses during speech are misinterpreted as sentence endings.

Innovation Solution

A GUI voice control apparatus that matches voice signals in real-time with command patterns without end point detection, using a context information generator to dynamically reflect GUI status and DB information in a language model, and a natural language recognizer to classify matching results, reducing the number of matchable command patterns and improving recognition speed and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If end point detection is used to determine sentence boundaries, then accuracy of voice recognition is maintained, but response time increases

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidresponse time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously analyzing voice signals in real-time and pre-identifying potential command patterns before the sentence fully completes. The natural language recognizer continuously processes incoming voice data against command patterns, allowing the system to be ready to execute commands immediately upon pattern recognition, rather than waiting for end point detection to confirm sentence completion.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the recognition process by continuously updating the analysis of voice signals as they are being spoken. The context information generator dynamically creates and updates language models based on current GUI status and database information, allowing the recognition system to adapt in real-time and identify commands during speech rather than requiring complete sentence detection.

Inventive Principle:
Principle #15Dynamics

2Loss of time

If pause interval threshold is shortened to increase response speed, then response time decreases, but accuracy deteriorates due to misinterpreting pauses as sentence endings

Engineering Contradiction:
Improveresponse timeVSAvoidvoice recognition accuracy
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The system uses feedback mechanisms where the natural language recognizer continuously monitors the voice signal and provides real-time feedback about pattern matching status. The context information generator receives feedback about current recognition state and dynamically adjusts the language model accordingly, allowing the system to distinguish between intentional pauses and sentence endings based on the context and pattern recognition progress rather than relying on fixed pause thresholds.

Inventive Principle:
Principle #23Feedback

3Productivity

If real-time matching without end point detection is implemented, then response speed increases, but system complexity increases

Engineering Contradiction:
Improvevoice recognition speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system segments the voice recognition process into distinct functional modules: a context information generator that creates language models, a natural language recognizer that performs pattern matching, and a command execution unit. This segmentation allows each module to specialize in its function, making the overall complex system more manageable and maintainable while enabling real-time processing through parallel operation of these modular components.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The context information generator acts as an intermediary between the GUI status/database information and the natural language recognizer. It creates and maintains language models that bridge the gap between raw voice signals and command patterns, simplifying the recognition process by pre-processing and structuring the contextual information that the recognizer needs for real-time pattern matching.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3611723B1Graphical user interface voice control apparatus/system and method
Publication Date: 2022.05.04 ALTIMEDIA CORP
  • EP3611723B1 patent drawingFigure 1
  • EP3611723B1 patent drawingFigure 2
  • EP3611723B1 patent drawingFigure 3~4A

AI summary

Disclosed are a GUI voice control apparatus and method. More particularly, a GUI voice control apparatus according to an embodiment of the present disclosure includes a context information generator configured to dynamically reflect GUI status information and DB information in a language model to generate context information; a voice recognizer configured to convert a voice signal into text in real time to update text information; a natural language recognizer configured to reduce the number of command patterns matchable with the text information based on the context information as the text information is updated, and recognize an intent and entity of the voice signal by matching with a final command pattern; and a voice controller configured to output a control signal according to the recognized intent and entity.