Local Voice Command Storage for Display Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing display devices require association with a server to execute voice commands, leading to increased time for processing and functionality execution.

Innovation Solution

A display device capable of storing frequently uttered voice commands, allowing it to perform natural language recognition processing independently without server association, using a voice recognition system that includes a voice recognition unit, STT DB, NLP client, and NLP DB to match voice commands with prestored patterns and perform intended functions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the display device is associated with a server to execute voice commands, then the voice recognition processing can be performed, but the time required to execute the voice command increases

Engineering Contradiction:
Improvevoice recognition processing capabilityVSAvoidtime required to execute voice command
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-storing frequently uttered voice commands and their corresponding intent analysis results in the display device before they are needed. When a user utteres a voice command, the system checks the stored data first, and if a match is found, the intent analysis result is immediately executed without requiring server connection. This pre-preparation of common voice command mappings eliminates the time delay that would otherwise occur during server communication for frequently used commands.

Inventive Principle:
Principle #10Preliminary action

2Loss of time

If the display device stores frequently uttered voice commands locally, then the execution time is reduced, but the device complexity increases

Engineering Contradiction:
Improveexecution time of voice commandVSAvoidvoice recognition system structure
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent applies the extraction principle by separating the voice recognition system into two distinct parts: a simple local storage component that stores frequently uttered voice commands and their intent results, and a server component that handles more complex or uncommon voice recognition tasks. This extraction allows the display device to perform basic voice command execution locally without requiring complex processing capabilities, thus reducing the overall device complexity while still enabling fast local execution for common commands.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent uses copying by creating a simplified local copy of the voice command recognition system that contains only the most frequently uttered commands and their pre-analyzed intent results. This copy is stored in the display device's memory and can be immediately executed without server connection. The copying approach allows the device to have a reduced complexity version of the full voice recognition system available locally, enabling fast response for common commands while maintaining the option to connect to the server for more complex tasks.

Inventive Principle:
Principle #26Copying

3Productivity

If the display device performs natural language recognition processing independently, then server association is eliminated, but the processing capability required in the device increases

Engineering Contradiction:
Improvevoice command execution speedVSAvoidnatural language recognition processing capability
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies partial action by implementing natural language recognition processing capability only for the most frequently uttered voice commands in the display device, rather than implementing the full capability for all possible commands. The system stores pre-processed intent analysis results for common commands locally, enabling immediate execution. For less common or complex commands, the system can still connect to the server for processing. This partial implementation approach allows the device to achieve high productivity for the most critical voice commands without requiring excessive processing capability for all possible language recognition tasks.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3190512B1Display device and operating method therefor
Publication Date: 2022.04.20 LG ELECTRONICS INC
  • EP3190512B1 patent drawingFigure 1
  • EP3190512B1 patent drawingFigure 2
  • EP3190512B1 patent drawingFigure 3

AI summary

A display device operating method, according to one embodiment of the present invention, comprises the steps of: receiving a voice command of a user; storing the voice command, if a function of the display device corresponding to the received voice command is not stored and the voice command is received at reference frequency or more; and if the voice command is received again, performing a function of the display device corresponding to the voice command received again.