GROUPING DOCUMENTS AND DATA OBJECTS VIA MULTI-CENTER CANOPY CLUSTERING

摘要

A canopy clustering process merges at least one set of multiple single-center canopies together into a merged multi-center canopy. Multi-center canopies, as well as the single-center canopies, can then be used to partition data objects in a dataset. The multi-center canopies allow a canopy assignment condition constraint to be relaxed without risk of leaving any data objects in a dataset outside of all canopies. Approximate distance calculations can be used as similarity metrics to define and merge canopies and to assign data objects to canopies. In one implementation, a distance between a data object and a canopy is represented as the minimum of the distances between the data object and each center of a canopy (whether merged or unmerged), and the distance between two canopies is represented as the minimum of the distances for each pairing of the center(s) in one canopy and the center(s) in the other canopy.

主权项

1. A computer-implemented process for grouping similar objects, comprising:
using a computer to perform process actions for:
receiving a document library comprising a plurality of data objects;mapping multiple subsets of the data objects to individual single center canopies, each center corresponding to one of the mapped data objects;merging two or more of the single center canopies into a corresponding multi-center canopy, each multi-center canopy having at least two separate centers each corresponding to a different mapped data object;assigning each data object of the document library to one or more of the multi-center canopies and unmerged single center canopies; andforming one or more clusters of one or more data objects from data objects assigned to the same canopy;outputting one or more of the clusters as a set of similar data objects.