Voice Command Intent Routing for Application-Specific Multimedia Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing speech recognition technologies primarily focus on accurately recognizing user utterances without considering the user's intent or optimizing services for specific applications, particularly in devices like mobile phones and smart TVs.

Innovation Solution

A multimedia device equipped with a memory, application manager, and controller that processes speech-based commands by transmitting data to a server for intent recognition and application-specific functionality, allowing for tailored speech recognition services based on the user's intent and ambient environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If speech recognition is optimized for accurate content recognition only, then recognition accuracy is improved, but user intent detection capability deteriorates

Engineering Contradiction:
Improverecognition accuracyVSAvoiduser intent detection
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The speech recognition system is divided into separate functional modules: a speech recognition module for accurate content recognition and an intent recognition module for detecting user intent. This segmentation allows each module to specialize in its specific function while working together to provide comprehensive speech processing capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary intent recognition module that bridges the gap between speech content recognition and application execution. This intermediary analyzes the recognized speech content to determine user intent, enabling the system to understand not just what was said but what the user wants to achieve.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If speech recognition service is configured to be device-specific, then device compatibility is improved, but application-specific optimization deteriorates

Engineering Contradiction:
Improvedevice compatibilityVSAvoidapplication-specific service quality
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The speech recognition system is designed with universal device compatibility while incorporating application-specific optimization capabilities. The system can adapt to different devices (smart TVs, mobile phones, tablets) and simultaneously provide tailored speech recognition services for specific applications through the intent recognition module that considers application context.

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

3Adaptability or versatility

If the number of applications is increased exponentially, then system functionality is improved, but service optimization complexity deteriorates

Engineering Contradiction:
Improvesystem functionalityVSAvoidservice optimization complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system automatically adapts to different applications and devices without requiring manual configuration for each combination. The intent recognition module self-adjusts based on the application context and device type, enabling the system to handle exponentially increasing numbers of applications while maintaining service optimization through automated adaptation rather than manual configuration.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3888080B1Multimedia device for processing voice command
Publication Date: 2026.01.21 LG ELECTRONICS INC
  • EP3888080B1 patent drawingFigure 1
  • EP3888080B1 patent drawingFigure 2
  • EP3888080B1 patent drawingFigure 3

AI summary

The present invention discloses a multimedia device capable of processing a recognized speech-based command. In one embodiment, the device may include a memory to store at least one application therein; an application manager for executing any of the at least one application stored in the memory; and a controller configured to receive from the application manager a list of at least one recognized speech-based command that can be executed by the executed application, wherein the controller is configured: to control a network interface module to transmit any speech-based data received from an outside and the list to the server; and to control the executed application or execute a function non-specific to the currently-executed application, based on a feedback result value received from the server via the network interface module.