Automated Asset Tag Ranking for Cloud Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The management of large numbers of cloud computing assets is impractical due to inconsistent and error-prone manual tagging, leading to challenges in maintaining classification policies across multiple providers and internal organizations, which affects the accuracy of predictive modeling systems.
Innovation Solution
A computerized tag ranking system calculates efficacy values for asset contexts, normalizes relevance values, and generates reason codes to improve the quality of tags in a ground truth set, enabling more accurate predictive modeling by ranking and refining tags based on historical usage and ambiguity analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual tagging is used for cloud computing assets, then asset classification can be performed, but the tagging becomes inconsistent and error-prone
Solution Approach 1:
The system enables self-service automated tagging by using machine learning models to automatically generate and assign asset tags based on analyzed data, eliminating the need for manual tagging operations while maintaining consistency and accuracy across all assets
Solution Approach 2:
The patent replaces the mechanical manual tagging process with an automated computational system that uses data analysis, machine learning algorithms, and automated tag generation to perform classification, thereby substituting human-operated mechanical tagging with an automated electronic system that improves reliability
2Loss of information
If multiple categories are used to categorize cloud computing assets, then complete visibility into all assets is achieved, but the complexity of managing classification policies increases
Solution Approach 1:
The system segments the complex multi-category classification problem into manageable components by using multiple specialized machine learning models, each trained to identify specific asset attributes and tags, allowing the system to handle complex classification requirements through divided, specialized processing units
Solution Approach 2:
The patent introduces an intermediary automated tag generation system that mediates between raw asset data and final classification policies, using machine learning models to translate data into standardized tags that simplify policy management while maintaining comprehensive asset visibility
3Quantity of substance
If manual tagging is performed across large numbers of assets, then asset classification can be achieved, but the process becomes impractical
Solution Approach 1:
The system replaces manual tagging mechanics with automated machine learning-based tag generation that can process large volumes of assets simultaneously, achieving high productivity by substituting human-operated sequential tagging with parallel computational processing
Solution Approach 2:
The patent changes the operational parameters from manual human tagging to automated computational tagging, fundamentally altering the speed and scale at which assets can be classified, enabling the system to handle large quantities of assets with high productivity
4Measurement precision
If training data quality is improved through better tags, then predictive modeling accuracy increases, but the effort to refine and rank tags increases
Solution Approach 1:
The system performs preliminary automated tag refinement and ranking actions before the predictive modeling training process, using machine learning models to pre-process and optimize tag quality in advance, thereby improving modeling accuracy without requiring additional time during the actual training phase
Solution Approach 2:
The patent replaces manual tag refinement mechanics with automated machine learning-based tag ranking systems that efficiently optimize tag quality through computational algorithms, reducing the time investment required compared to manual refinement processes
Data Source
AI summary
An embodiment includes calculating an efficacy value of a context assigned to an asset, the efficacy value being based at least in part on a percentage of assets assigned to the context. The embodiment also includes calculating, responsive to the calculated efficacy value being within a predetermined range, a normalized relevance value of a first tag associated with the asset. The embodiment also includes generating relative relevance value for the first tag and a reason code associated with a basis for the relative relevance value of the first tag based at least in part on the normalized relevance value of the first tag. The embodiment also includes initiating, responsive to generating the relative relevance value and the reason code for the first tag, a database command on a training dataset stored in the database that includes the first tag.