Hierarchical Data Set Classification and Network Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for automatically ranking and mapping network structures are inefficient, incomplete, inaccurate, and dependent on human mediation, particularly when dealing with complex networks that have hierarchical organization beyond two levels, such as biological and social systems.
Innovation Solution
A computer-implemented method and system for hierarchically classifying, ranking, and labeling data sets by determining a network of documents based on directed edges, which defines nested modules and provides a visual indication of these modules, allowing for navigation and identification of changes in network structure over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current techniques for automatically ranking and mapping network structures are used, then some level of classification is achieved, but the process is inefficient, incomplete, and inaccurate for complex hierarchical networks
Solution Approach 1:
The patent segments the complex network analysis task into multiple hierarchical levels, where the system automatically identifies and processes different tiers of modules and submodules. This segmentation allows the system to handle complex hierarchical structures by breaking them down into manageable levels, improving both accuracy and efficiency in classifying network relationships.
Solution Approach 2:
The patent implements nested doll by creating a hierarchical classification system where modules contain submodules, which in turn contain further subdivisions. This nested structure enables the system to capture deep hierarchical relationships in complex networks, allowing for more complete and accurate classification while maintaining organizational efficiency through the nested architecture.
2Extent of automation
If current techniques are used to classify networks beyond two levels, then deeper structural relationships can be identified, but the process becomes time-consuming and dependent on human mediation
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform hierarchical classification without human intervention. The system autonomously identifies modules, submodules, and their relationships across multiple hierarchical levels, eliminating the need for time-consuming manual mediation while maintaining high accuracy in detecting deep structural relationships in complex networks.
3Reliability
If hierarchical partitioning is applied to reveal deeper network structures, then more complete classification is achieved, but the complexity of the system increases
Solution Approach 1:
The patent applies nested doll by organizing the classification system into hierarchical levels where each level contains and is contained by the next. This nested architecture provides a structured framework that manages system complexity while enabling complete classification of deep hierarchical networks, as each nested level handles a specific tier of the hierarchy independently.
Solution Approach 2:
The patent segments the hierarchical classification into distinct levels and modules, where each segment handles a specific portion of the hierarchical structure. This segmentation reduces overall system complexity by dividing the complex task of multi-level hierarchical classification into manageable, independent segments that can be processed separately and systematically.
Data Source
AI summary
Described herein are methods and systems for hierarchically mapping, ranking, and labeling data sets automatically. Also provided are methods for browsing and navigating a hierarchically mapped data set, and START identifying changes in network structure over time. An example method may involve receiving document data indicating a corpus of documents and references between documents within the corpus. Based on the document data, a network comprising two or more nodes and at least one directed edge may be determined. Also, a hierarchical partition of the documents may be determined based on the directed edges of the network. The hierarchical partition may define a plurality of nested modules, and each module in the plurality of nested modules may be associated with one or more respective documents within the corpus. The method may additionally include causing a graphical display to provide a visual indication of one or more of the plurality of nested modules.