Distributed OCR and Translation Task Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile computing devices face challenges in efficiently performing optical character recognition (OCR) and machine language translation due to limitations in processing power and network delays, especially when dealing with complex images and texts that require higher processing capabilities.
Innovation Solution
A distributed approach is implemented, where the mobile computing device determines the complexity of OCR and translation tasks and selectively offloads them to servers based on predefined thresholds, allowing it to perform tasks within its capabilities while delegating more complex tasks to servers, thereby optimizing processing and reducing network delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If mobile computing device performs OCR and translation independently, then processing speed is improved, but processing accuracy deteriorates for complex tasks
Solution Approach 1:
The patent segments OCR and translation tasks into two categories: simple tasks handled locally by the mobile device and complex tasks handled by remote servers. This segmentation allows the system to optimize for speed on simple tasks while maintaining high accuracy on complex tasks through server processing.
Solution Approach 2:
The system dynamically changes the processing parameter (local vs. remote execution) based on task complexity assessment. When complexity exceeds thresholds, the system transitions from local processing to remote server processing, thereby adapting accuracy and speed parameters to match task requirements.
2Loss of time
If mobile computing device performs all tasks independently, then network delays are reduced, but processing capability is insufficient for complex tasks
Solution Approach 1:
The system performs partial processing locally for all tasks (initial assessment and simple task execution), and only offloads to servers when necessary. This partial local action minimizes network delays for simple tasks while reserving server capability for complex tasks that exceed local processing capacity.
Solution Approach 2:
The mobile device acts as an intermediary that assesses task complexity and routes appropriate tasks to servers. This intermediary role optimizes the balance between local processing speed and server processing capability, reducing unnecessary network delays while maintaining processing capability for complex tasks.
3Measurement precision
If complex tasks are offloaded to servers, then processing accuracy is improved, but network dependency increases
Solution Approach 1:
The system implements local quality assessment by evaluating task complexity characteristics (image resolution, text density, language pair rarity) to determine whether to process locally or remotely. This local quality control mechanism optimizes accuracy for complex tasks while minimizing network dependency for simple tasks.
4Use of energy by moving object
If simple tasks are processed locally, then energy consumption is reduced, but processing accuracy may be insufficient
Solution Approach 1:
The system dynamically changes the processing location parameter based on task complexity. For simple tasks, it maintains local processing to conserve energy; for complex tasks, it transitions to server processing to ensure accuracy, thereby optimizing the energy-accuracy tradeoff.
Data Source
AI summary
A technique for selectively distributing OCR and/or machine language translation tasks between a mobile computing device and server(s) includes receiving, at the mobile computing device, an image of an object comprising a text. The mobile computing device can determine a degree of optical character recognition (OCR) complexity for obtaining the text from the image. Based on this degree of OCR complexity, the mobile computing device and/or the server(s) can perform OCR to obtain an OCR text. The mobile computing device can then determine a degree of translation complexity for translating the OCR text from its source language to a target language. Based on this degree of translation complexity, the mobile computing device and/or the server(s) can perform machine language translation of the OCR text from the source language to a target language to obtain a translated OCR text. The mobile computing device can then output the translated OCR text.