Hierarchical Clustering for Large-Scale Data Pattern Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to efficiently manage and analyze large-scale data sets, particularly in visualizing patterns and trends within these datasets, due to the complexity and size of the data, which hinders user interaction and perceptibility.
Innovation Solution
A method and system that employs hierarchical-based clustering to classify data points into groups, using Delaunay triangulation and minimum spanning trees, followed by convex hull optimization to generate geometrical shapes representing data clusters, facilitating interactive visualization and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If large-scale data sets are visualized using traditional methods, then complete data representation is achieved, but rendering complexity and computational burden increase significantly
Solution Approach 1:
The patent segments large-scale data sets into multiple clusters using hierarchical clustering algorithms. Instead of rendering all individual data points, the system divides the data space into clusters and represents each cluster with simplified geometric shapes, dramatically reducing rendering complexity while preserving data patterns and relationships.
Solution Approach 2:
The patent inverts the traditional visualization approach by not directly representing individual data points, but rather representing clusters of data points through geometric shapes. This inversion transforms the problem from rendering numerous individual elements to rendering a manageable number of cluster representations, effectively reducing computational burden.
2Measurement precision
If detailed data points are displayed individually, then data precision is maintained, but user perceptibility and interaction efficiency deteriorate
Solution Approach 1:
The patent merges multiple individual data points into cluster groups, where each cluster is represented by a single geometric shape. This merging maintains the precision of underlying data through cluster properties while improving user interaction efficiency by reducing the number of discrete elements users must process and interact with.
Solution Approach 2:
The patent creates simplified geometric shape copies that represent complex clusters of data points. These geometric copies serve as proxies that maintain the essential characteristics and relationships of the original data while being much easier to perceive and interact with, thus improving user efficiency without completely sacrificing data fidelity.
3Device complexity
If geometric shapes are used to represent data clusters, then rendering complexity is reduced, but data representation accuracy may be compromised
Solution Approach 1:
The patent applies local quality by using different geometric shapes and visual properties to represent different clusters based on their specific characteristics. Each cluster's geometric representation is tailored to reflect its local data distribution and properties, ensuring that the simplification does not uniformly compromise accuracy across all data regions.
Solution Approach 2:
The patent changes parameters of geometric shapes (such as size, shape, color, and position) to encode different cluster properties and data characteristics. By varying these parameters, the system maintains rich data representation information within simplified geometric forms, reducing rendering complexity while preserving essential data accuracy.
Data Source
AI summary
Disclosed are systems and methods for extracting and visualizing patterns in large-scale data sets. A data set comprising a plurality of data points is received. A plurality of connections between the plurality of data points is generated. Based on the plurality of connections, a plurality of groups from the plurality of data points is generated. A visual analytic comprising a plurality of geometrical shapes corresponding to the plurality of groups is generated.