Interface Text Translation via OCR and Overlay Rendering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for translating text in applications are inefficient, requiring manual input and simultaneous display of multiple interfaces, which is time-consuming and lacks real-time performance, especially for dynamic content like games with many pages.

Innovation Solution

A method and apparatus that automatically acquire, translate, and display text within an application's interface by determining text regions, using machine translation, and storing translation results for quick retrieval, allowing real-time translation without manual input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual input method is used to translate text in target application, then translation can be performed, but time consumption increases and translation efficiency decreases

Engineering Contradiction:
Improvetranslation efficiencyVSAvoidtime consumption
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system enables self-service translation by automatically capturing text from the target application interface, performing OCR recognition, and translating without requiring manual user input. The translation application autonomously completes the entire workflow from text acquisition to translation display.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual input process with automated optical character recognition (OCR) technology. The system uses image processing to capture and recognize text from the application interface, substituting the manual copying and pasting action with automated visual recognition and processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If translation application interface is displayed simultaneously with target application interface, then translation results can be viewed, but device complexity increases and user interaction becomes cumbersome

Engineering Contradiction:
Improveuser interaction efficiencyVSAvoidinterface management complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent merges the translation application interface with the target application interface by displaying translation results directly within the target application's interface. This integration eliminates the need for separate interface switching and provides a unified user experience.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The translation interface is nested within the target application interface, where the translation results are displayed as an overlay or embedded component within the original application context. This allows the translation functionality to be contained within the existing interface structure.

Inventive Principle:
Principle #7Nested doll (Nesting)

3Productivity

If text is copied manually from target application to translation application, then translation can be performed, but operation complexity increases and productivity decreases

Engineering Contradiction:
Improvetranslation throughputVSAvoidoperation simplicity
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system extracts text directly from the target application interface through automated screenshot capture and OCR recognition, eliminating the need for manual text selection and copying. The text is pulled out from its visual context and prepared for translation automatically.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11907649B2Method and apparatus for managing interface, device and readable storage medium
Publication Date: 2024.02.20 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • US11907649B2 patent drawing
  • US11907649B2 patent drawing
  • US11907649B2 patent drawing

AI summary

A method and apparatus for managing an interface, a device and a non-transitory computer readable storage medium. The method includes: acquiring a first interface image of a target application, determining a first text contained in the first interface image, the first text being a text in a first language corresponding to the target application, acquiring a second text obtained by translating the first text, the second text being a text in a second language, and replacing the first text in the first interface image with the second text to obtain a second interface image, and displaying, based on the target application, the second interface image.