Voice Command Management via Local Server Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice command systems in electronic devices experience delays due to server management, leading to inconvenience in repeated operations of speech recognition functions.

Innovation Solution

A voice command providing system that transmits audio data to a server device for analysis and registers specific audio data as voice commands, allowing for prompt function execution without relying on server management, and efficiently manages voice commands by converting frequently used functions and removing unused ones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If voice data is transmitted to a server device for speech recognition, then the reliability of speech recognition result is improved, but the response time increases due to network transmission and server processing delays

Engineering Contradiction:
Improvespeech recognition result reliabilityVSAvoidresponse time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The speech recognition system is segmented into two parts: frequently used commands are recognized locally by the electronic device for immediate response, while other commands are transmitted to the server device for recognition. This segmentation allows critical functions to operate without server delays while maintaining overall system reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The electronic device pre-loads and stores recognition results for frequently used voice commands in its local memory. When a user issues a common command, the device can immediately retrieve the pre-stored result without waiting for server processing, significantly reducing response time for routine operations.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If all voice commands are processed through server management, then the accuracy of speech recognition is improved, but the operational efficiency decreases due to repeated network transmissions

Engineering Contradiction:
Improvespeech recognition accuracyVSAvoidoperational efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system applies different processing qualities to different voice commands based on their frequency of use. Frequently used commands receive local processing with immediate response, while less common commands are transmitted to the server for full accuracy processing. This local quality approach optimizes overall operational efficiency while maintaining adequate accuracy for all commands.

Inventive Principle:
Principle #3Local quality

3Speed

If the electronic device stores and manages voice commands locally, then the response speed is improved, but the device complexity increases due to additional memory and management requirements

Engineering Contradiction:
Improvevoice command response speedVSAvoidvoice command management complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The system extracts only the essential elements for local storage: recognition results and frequency information for frequently used voice commands. By taking out only what is necessary for local processing rather than storing complete command databases, the device achieves fast response speeds while minimizing the increase in complexity and memory requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3826005B1Method of providing voice command and electronic device supporting the same
Publication Date: 2025.01.01 SAMSUNG ELECTRONICS CO LTD
  • EP3826005B1 patent drawingFigure 1
  • EP3826005B1 patent drawingFigure 2
  • EP3826005B1 patent drawingFigure 3

AI summary

An electronic device, a method, and a chip set are provided. The electronic device includes a memory configured to store at least one of audio feature data of audio data and speech recognition data obtained by speech recognition of audio data; and a control module connected to the memory, wherein the control module is configured to update a voice command that is set to execute a function through voice, the function being selected based on at least one of the audio feature data, the speech recognition data, and function execution data executed in relation to the audio data.