Data Classification via Format Organization Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional data classification methods are inefficient, requiring analysis of all data classes for each data item, leading to prolonged processing times, especially when dealing with large volumes of data.
Innovation Solution
The method determines format organizations of data items, selecting a subset of data classes based on symbol types and their occurrences, reducing the number of classes that need to be analyzed, thereby classifying data items into target classes efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional data classification methods analyze all data classes for each data item, then classification accuracy is maintained, but processing time increases significantly
Solution Approach 1:
The patent segments the data classification process into two distinct phases: (1) format organization analysis phase where data items are analyzed to determine their format organizations (continuous symbols, discrete symbols, delimiters), and (2) candidate class selection phase where only relevant data classes are considered based on the format organization. This segmentation allows the system to maintain classification accuracy by systematically evaluating format characteristics while significantly reducing processing time by avoiding analysis of all possible data classes for every item.
Solution Approach 2:
The patent applies preliminary action by performing format organization analysis before conducting the actual data class classification. The system first identifies the format organization characteristics of data items (such as continuous symbol sequences, discrete symbol patterns, and delimiter structures), then uses these pre-analyzed format characteristics to pre-filter and select candidate data classes. This preliminary format analysis creates a foundation that guides the subsequent classification step, ensuring accuracy is maintained while reducing the scope of the final classification operation.
2Adaptability or versatility
If all data classes are analyzed for each data item, then comprehensive classification coverage is achieved, but system complexity increases
Solution Approach 1:
The patent divides the complex classification system into modular components: a format organization analysis module that identifies structural patterns in data items, and a candidate class selection module that maps format organizations to relevant data classes. This modular segmentation maintains comprehensive classification coverage by ensuring all data class possibilities are considered through the systematic format analysis, while reducing system complexity by organizing the classification logic into distinct, manageable modules with clear interfaces.
Solution Approach 2:
The patent introduces format organization as an intermediary concept between raw data items and final data class classifications. Instead of directly comparing each data item against all possible data classes (which would create system complexity), the system first transforms data items into format organization representations that capture their structural characteristics. This intermediary representation then serves as the basis for selecting candidate data classes, simplifying the overall system architecture while maintaining comprehensive classification coverage.
Data Source
AI summary
Provided is a method, computer program product, and system for classifying a set of data items based on format organizations. A processor may determine at least one format organization of a set of data items. The format organization of a data item indicates a symbol type of at least one continuous symbol in the data item and a number of the at least one continuous symbol. The processor may determine at least one candidate data class for the set of data items from a plurality of predetermined data classes based on the at least one format organization. The processor may classify the set of data items into at least one target data class selected from the at least one candidate data class. In this way, the set of data items can be efficiently classified.