Back to results
US 2015/0269494 A1Published application
Graph-based organization entity resolution
AssigneeIntelius
InventorsHakan KARDES, Deepak KONIDENA, Siddharth AGRAWAL, Micah HUFF, Ang SUN, Lin CHEN, Andrew KELLBERG, Xin WANG
Life of this patent
Estimating the term…
Abstract
A novel entity resolution approach for the organization entity domain can be implemented in the MapReduce framework with low memory requirements so that it may scale to large scale datasets. A new clustering approach, sClust, significantly improves the recall of the pairwise classifier.
Claims10
A machine learning system comprising:
- a distributed memory arrangement that provides sorted edge lists for each connected component;
- and
- a distributed processing arrangement coupled to the distributed memory arrangement, the distributed processing arrangement being configured to generate node structures and conflict sets in a first pass, and in a second pass to agglomeratively construct clusters for scores exceeding a match threshold.
The machine learning system of claim 8 wherein for any distinct connected component (Ci,Cf)εC, there is no path between any pair vk and vl where vkεCi,vlεCj.
Dependencies are inferred from the claim text.