Aggregated Multi-Module Data Classification System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data classification systems often produce inaccurate classifications, leading to improper storage and handling of sensitive data, which can result in non-compliance with regulations and security breaches, as they may incorrectly categorize personal or sensitive information.
Innovation Solution
The system employs multiple classification modules, including dictionary, regular expression, and machine learning modules, to generate proposed classifications with confidence levels, which are then aggregated to determine a final classification, ensuring more accurate data categorization and compliance with regulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single classification module is used, then the system complexity is low, but the classification accuracy is insufficient leading to improper handling of sensitive data
Solution Approach 1:
The system divides the classification task into multiple specialized modules (dictionary-based classifier, machine learning classifier, regex-based classifier), each handling specific aspects of data classification. This segmentation allows each module to focus on particular patterns or data types, improving overall classification accuracy while maintaining manageable complexity through modular design
Solution Approach 2:
The patent combines multiple classification modules into a unified system that processes data through all modules and aggregates their results. The merging of different classification approaches (dictionary, ML, regex) creates a more robust system that leverages the strengths of each individual module to achieve higher classification accuracy
2Measurement precision
If multiple classification modules are used, then the classification accuracy improves, but the processing time increases
Solution Approach 1:
The system implements a confidence threshold mechanism where if any classification module produces a result above the threshold, the process can terminate early with that result. This partial action approach avoids running all modules to completion when a sufficiently confident classification is already available, reducing processing time while maintaining accuracy
Solution Approach 2:
The system uses multiple copies of classification logic implemented as separate modules with different methodologies. Rather than one complex sequential process, parallel copies of classification functions run simultaneously, and their results are aggregated, improving both accuracy and efficiency
3Reliability
If classification results are not aggregated, then the processing is simpler, but the reliability of classification decisions decreases
Solution Approach 1:
The aggregation mechanism implements feedback by comparing classification results from multiple modules and using confidence levels to validate decisions. The system feedback loop ensures that classifications are vetted through multiple perspectives, improving reliability while the automated aggregation process manages the complexity of coordinating multiple modules
Data Source
AI summary
The present disclosure relates to methods and systems to classify data. A set of classification modules may inspect received data and identify proposed classifications for confidence values for the received data. An aggregation module may receive and aggregate the proposed classifications and confidence values. Based on the aggregated proposed classifications and the confidence values, the aggregation module may generate a final classification for the received data. An external device may perform an action with respect to the received data based on the final classification associated with the data. The action performed may include maintaining the data such that the data may be retrieved upon receipt a request for the data. Any of the classification modules and the aggregation module may be based on training data that may be utilized in subsequent iterations of classifying data to increase classification accuracy.