Mobile Terminal Voice Recognition Text Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current mobile terminals face challenges in efficiently converting voice input to text and recognizing important portions of telephone conversations, as existing speech-to-text functions are time-consuming and difficult to navigate.

Innovation Solution

A mobile terminal system that includes a voice recognition module to convert voice input into text, with features like automatic insertion of recognized letters, editing capabilities, and multitasking support, allowing for efficient writing input and integration of voice-recognized text into the user's writing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If speech-to-text function is executed to convert voice input into text, then text conversion is achieved, but it takes a long time and user effort is excessive

Engineering Contradiction:
Improvetext conversion speedVSAvoidtime for voice-to-text conversion
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent segments the text conversion process by distinguishing between manually written input and automatically recognized voice input. The display unit separately shows writing input characters and voice-recognized characters, allowing the system to process and present text in distinct segments rather than as a single unified conversion process, thereby improving efficiency and user control.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary mechanism where the writing input serves as a reference for voice recognition. The voice recognition module uses the writing input as a mediator to identify and convert only the unmatched portion of voice input into text, reducing the overall conversion time and effort required compared to converting the entire voice input from scratch.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If speech-to-text function is executed to convert entire voice content, then complete text conversion is achieved, but it is difficult to recognize important portions

Engineering Contradiction:
Improvecompleteness of voice content conversionVSAvoidease of recognizing important content
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent applies local quality by displaying different types of characters with distinct visual characteristics. Writing input characters and voice-recognized characters are shown in different fonts or styles on the display unit, allowing users to easily distinguish and recognize important portions of the text based on their origin, thereby improving ease of operation while maintaining complete information.

Inventive Principle:
Principle #3Local quality

3Loss of information

If voice recognition converts all voice input to text, then complete transcription is achieved, but user effort and time consumption increase

Engineering Contradiction:
Improvecompleteness of voice transcriptionVSAvoidcomplexity of text input process
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent implements partial action by having the voice recognition module convert only the unmatched portion of voice input that is not already represented in the writing input. This partial conversion approach achieves complete transcription information while reducing the complexity of the overall text input process, as users don't need to manage complete conversion of all voice content.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2849055B1Mobile terminal and method of controlling the same
Publication Date: 2019.06.05 LG ELECTRONICS INC
  • EP2849055B1 patent drawingFigure 1
  • EP2849055B1 patent drawingFigure 2A~2B
  • EP2849055B1 patent drawingFigure 3

AI summary

A mobile terminal including a wireless communication unit configured to perform wireless communication; a microphone configured to receive an input voice; a touch screen; and a controller configured to receive a written touch input on the touch screen corresponding to the input voice, recognize the input voice while a voice recognition mode is activated, and display extracted information extracted from the recognized input voice on the touch screen based on a comparison of the recognized input voice and the written input.