Voice Input Text Matching Algorithm for Reducing Selection Operations

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice input methods require users to perform multiple selection operations to convert voice data into text, leading to increased complexity and reduced user experience.

Innovation Solution

A method and device that recognizes voice data, converts it into corresponding text, and displays the text in an input interface as a phrase or short sentence, utilizing state information and relationships between voice texts and target texts to simplify input operations through a matching algorithm.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional voice input methods are used, then voice data can be converted to text, but multiple selection operations are required which increases complexity and reduces user experience

Engineering Contradiction:
Improveuser input operationsVSAvoidselection operations complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically determines the most appropriate text from multiple candidate texts by analyzing voice characteristics, context, and pre-defined relationships, eliminating the need for users to manually select from candidate texts. The system serves itself by autonomously resolving ambiguity and selecting the correct text to be input.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system pre-establishes corresponding relationships between different voice texts and target texts before the matching process. By preparing these relationships in advance and using them in the matching algorithm, the system can quickly and accurately determine the intended text without requiring user intervention during the input process.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If multiple selection operations are required, then text can be converted accurately, but user experience is reduced and input efficiency decreases

Engineering Contradiction:
Improveinput efficiencyVSAvoiduser experience
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system autonomously completes the text selection process by using the matching algorithm to determine the most appropriate text from candidates, eliminating the need for user selection operations and thereby improving input efficiency while maintaining accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses feedback from voice characteristics, context analysis, and pre-defined relationships to continuously refine and determine the most appropriate text. This feedback mechanism enables the system to accurately identify user intent without requiring manual selection, thus improving both efficiency and user experience.

Inventive Principle:
Principle #23Feedback

3Speed

If voice text is directly used as input, then input speed is improved, but accuracy may be reduced without matching algorithms

Engineering Contradiction:
Improveinput speedVSAvoidtext accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The system pre-establishes corresponding relationships between voice texts and target texts, and uses these pre-prepared relationships in the matching algorithm to quickly and accurately determine the intended text. This preliminary preparation enables both fast processing and high accuracy simultaneously.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The matching algorithm acts as an intermediary between the voice text and the final text to be input. It uses pre-defined relationships and context analysis to bridge the gap between raw voice input and accurate text output, maintaining both speed and precision in the conversion process.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3644177B1Input method, device, apparatus, and storage medium
Publication Date: 2024.11.06 BEIJING XIAOMI MOBILE SOFTWARE CO LTD
  • EP3644177B1 patent drawingFigure 1
  • EP3644177B1 patent drawingFigure 2A
  • EP3644177B1 patent drawingFigure 2B

AI summary

The disclosure relates to a method, device, apparatus, and storage medium. The method includes recognizing voice data inputted by a user and obtaining a voice text corresponding to the voice data; obtaining, based on the voice text, a text to-be-input corresponding to the voice data, wherein the text to-be-input includes a plurality of words constituting a phrase or a sentence; and displaying the text to-be-input in an input textbox of an input interface.