Dual-Level Machine Learning Engine for Local Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional machine learning engines for system-wide data analysis require extensive computational resources, which is inefficient when data is not stored in a distributed manner, leading to a tradeoff between computational power and processing speed.
Innovation Solution
A dual-level machine learning engine system where a primary engine provides entity-wide data analysis insights and instructs secondary, locally hosted engines to refine these insights into specific local data trends, reducing the need for extensive computational resources and network traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional machine learning engines are used for system-wide data analysis, then comprehensive data processing capability is improved, but computational resource consumption increases
Solution Approach 1:
The patent divides the machine learning processing into two segments: a centralized first machine learning engine that performs system-wide data analysis, and multiple distributed second machine learning engines that perform local data analysis. This segmentation allows comprehensive data processing while reducing the computational burden on any single system, as local engines handle routine analysis independently.
Solution Approach 2:
The patent introduces a hierarchical dimension to the machine learning architecture, with engines operating at two levels: system-wide (centralized) and local (distributed). This dimensional change enables the system to process data comprehensively while reducing computational resource consumption by handling different types of analysis at appropriate levels.
2Ease of operation
If data is stored in a distributed manner across network devices, then data accessibility is improved, but processing speed deteriorates due to network traffic requirements
Solution Approach 1:
The patent extracts the machine learning processing capability from the centralized system and places it directly at the data source through second machine learning engines hosted on network devices. This extraction eliminates the need to transfer raw data over the network for analysis, maintaining data accessibility while significantly improving processing speed by performing analysis where the data resides.
3Measurement precision
If extensive computational resources are allocated for system-wide analysis, then analysis accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies different quality levels to different parts of the system: the first machine learning engine performs comprehensive system-wide analysis requiring extensive computational resources for high accuracy, while second machine learning engines perform localized analysis with reduced computational requirements. This local quality approach maintains high analysis accuracy where needed while reducing overall system complexity.
Data Source
AI summary
Systems, computer program products, and methods are described herein for processing data using an optimized machine learning architecture. The present disclosure is configured to monitor usage data for a plurality of network devices; analyze the usage data using a first machine learning engine; determine, based on an output of the first machine learning engine, at least one data trend; and instruct a second machine learning engine to analyze local data associated with the at least one data trend, wherein the second machine learning engine is hosted on a first network device of the plurality of network devices.