Patent · US Active

System for identifying duplicate parties using entity resolution

US11556845B2 · kind B2 · utility

0Cited by
9References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 29, 2019
Grant dateJan 17, 2023
Priority date
Expiry dateJul 28, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N7/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An entity resolution system performs a method of resolving one or more candidate entities based on a data set. The entity resolution system has a machine learning module and a narrative module. The machine learning module generates a synthesized data set, the synthesized data set comprising similarity ratings for each entity feature. The narrative module applies a clustering analysis to determine one or more distances between the group of similarity ratings for each entity feature and one or more clusters associated with known relationships between entities, generates a narrative output based on one or more distances. The narrative output states at least one identified relationship between at least two entities of the plurality of candidate entities and a confidence score. The narrative engine also provides the narrative output to a user interface.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.