Text Correction Using Audio Input Context

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional autocorrect programs in information handling devices often fail to accurately correct misspelled words, especially proper names, and can change correctly spelled words without considering sentence context, leading to incorrect modifications and user frustration.

Innovation Solution

The method involves receiving electronic text input and an additional input, such as audio, to modify the text based on the secondary input, using context data to determine the user's intended correction, and providing the modified text on a display device.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional autocorrect programs modify electronic text based on best guesses, then text correction is provided, but accuracy of correction deteriorates leading to incorrect modifications

Engineering Contradiction:

Improvecorrection accuracyVSAvoiduser intent detection precision

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent combines multiple input modalities (audio input and text input) into a unified correction system. The audio input device captures spoken corrections while the text input device captures typed corrections, and both are processed together to determine user intent, thereby improving correction accuracy over single-modality systems

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system introduces an intermediary processing layer that receives corrections from multiple sources (audio and text inputs), analyzes them against the original electronic text, and determines the most likely user intent before applying corrections. This intermediary layer acts as a mediator between raw input and final correction output

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If autocorrect programs suggest alternative words for user selection, then correction options are provided, but user operation time increases due to additional selection steps

Engineering Contradiction:

Improvecorrection accuracyVSAvoiduser operation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of potential corrections by comparing audio and text inputs against the original electronic text before presenting options to the user. This preliminary filtering reduces the number of correction options the user must evaluate, saving time while maintaining accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies partial correction by only processing and presenting corrections that show sufficient confidence matches between the correction input and original text. This selective approach avoids presenting excessive options to the user, reducing decision time while maintaining high accuracy

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10726197B2Text correction using a second input

Publication Date: 2020.07.28 LENOVO SWITZERLAND INTERNATIONAL GMBH

AI summary

One embodiment provides a method including receiving, at a key input device, an electronic text input; obtaining, using a processor, an additional input comprising audio and relating to the electronic text input; modifying, using a processor, the electronic text input based upon the additional input; and providing, on a display device, electronic text which has been modified. Other aspects are described and claimed.