On-Device AI Workload Distribution for Speed and Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
On-device AI processing faces limitations in processing speed and accuracy, particularly in noisy environments or with long texts, compared to server or cloud-based AI processing.
Innovation Solution
An on-device AI processing system that distributes AI processing load to external or internal devices when the terminal's capacity is exceeded, combining local and external AI processing results to enhance performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If on-device AI processing is used, then processing speed is improved, but processing accuracy deteriorates
Solution Approach 1:
The patent segments AI processing into two parts: simple tasks processed locally on the terminal device for speed, and complex tasks processed on external servers for accuracy. The processor divides incoming AI processing requests based on complexity thresholds, routing appropriate portions to different processing locations.
Solution Approach 2:
The patent merges on-device AI processing capabilities with external server AI processing capabilities into a unified system. The terminal device combines local processing results with remote processing results to achieve both speed and accuracy benefits.
2Reliability
If on-device AI processing is used, then privacy protection is improved, but processing completeness deteriorates
Solution Approach 1:
The patent applies local quality by keeping sensitive data processing local to the terminal device while allowing non-sensitive or less sensitive data to be processed externally. Different processing locations are assigned based on the sensitivity and complexity requirements of specific AI tasks.
3Use of energy by moving object
If on-device AI processing is used, then cost is reduced, but processing capability deteriorates
Solution Approach 1:
The patent implements dynamic processing capability adjustment where the terminal device can flexibly switch between local-only processing, hybrid processing, and server-reliant processing based on available resources, task requirements, and performance needs. This allows the system to adapt its processing capability dynamically.
Data Source
AI summary
An on-device artificial intelligence (AI) processing distributed processing device and method capable of distributing AI processing load of a terminal through internal or external other devices are provided. The on-device AI processing distributed processing device can, measure an amount of AI processing for performing the user command, select an AI processing distributed processing target when the measured amount of AI processing exceeds a self-processing capacity, request distributed process for AI processing to the selected AI processing distributed processing target, and when a first AI processing result value is received from the AI processing distributed processing target, provide a final result value based on the first AI processing result value and a self-processed second AI processing result value.