Data Clustering Method Reducing Computational Complexity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data clustering methods are inefficient in rapidly and accurately grouping data with similar features into categories, leading to increased computational complexity and reduced speed performance.
Innovation Solution
A method and apparatus for clustering that involves acquiring inter-sample similarity between data samples, merging them into initialization clusters based on similarity thresholds, and further clustering and merging these clusters to reduce the number of initialization clusters, thereby improving clustering speed and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional data clustering methods are used, then data can be grouped into categories, but computational complexity increases and clustering speed decreases
Solution Approach 1:
The patent segments the clustering process into two distinct stages: first, merging similar data samples into initialization clusters based on inter-sample similarity; second, further clustering and merging these initialization clusters. This segmentation reduces computational complexity by performing coarse-grained clustering first, then refining it, thereby improving overall clustering speed without sacrificing accuracy.
Solution Approach 2:
The patent applies preliminary action by pre-merging data samples into initialization clusters before the main clustering process. This preliminary organization of data into N initialization clusters (where N < M) reduces the number of elements that need to be processed in subsequent clustering operations, directly reducing computational complexity and enhancing clustering speed.
2Measurement precision
If more data samples are processed, then clustering accuracy improves, but processing time increases
Solution Approach 1:
By segmenting the clustering process into two stages, the patent can process large datasets efficiently. The first stage creates initialization clusters that capture major data structures, while the second stage refines these clusters with higher precision. This segmentation allows the system to maintain accuracy even as data volume increases, as each stage handles a portion of the computational load.
Solution Approach 2:
The preliminary merging of data samples into N initialization clusters creates a structured foundation that simplifies subsequent processing. This pre-organization reduces the time required for the main clustering operation, as the algorithm only needs to refine existing cluster structures rather than build them from scratch, thereby reducing processing time while maintaining accuracy.
Data Source
AI summary
The present disclosure provides a clustering method and apparatus and an electronic device. The method includes: acquiring an inter-sample similarity between every two pieces of sample data in M pieces of sample data, where M is a positive integer; merging the M pieces of sample data into N initialization clustered clusters according to the acquired inter-sample similarity, where N is a positive integer smaller than M; and clustering and merging the N initialization clustered clusters to obtain multiple clustered clusters corresponding to the M pieces of sample data.