US 12,216,683 B1
Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis
Yuang Tang, Baltimore, MD (US)
Assigned to Federal Home Loan Mortgage Corporation (Freddie Mac), McLean, VA (US)
Filed by FEDERAL HOME LOAN MORTGAGE CORPORATION (FREDDIE MAC), McLean, VA (US)
Filed on Jul. 31, 2023, as Appl. No. 18/362,375.
Application 18/362,375 is a continuation of application No. 17/557,382, filed on Dec. 21, 2021, granted, now 11,748,379.
Application 17/557,382 is a continuation of application No. 16/671,143, filed on Oct. 31, 2019, granted, now 11,238,065, issued on Feb. 1, 2022.
Application 16/671,143 is a continuation of application No. 15/593,113, filed on May 11, 2017, granted, now 10,496,678, issued on Dec. 3, 2019.
Claims priority of provisional application 62/335,580, filed on May 12, 2016.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/28 (2019.01); G06F 16/29 (2019.01)
CPC G06F 16/282 (2019.01) [G06F 16/29 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for performing machine learning for a knowledge graph computer system, the method comprising:
obtaining home location data from a knowledge graph;
inputting the home location data into a machine learning model, the machine learning model configured to perform classification;
training the machine learning model based on the home location data, the training comprising:
learning one or more boundaries for a neighborhood; and
determining a generalization based on the home location data;
generating, based on the trained machine learning model, at least one of a neighborhood membership or an identified neighborhood; and
updating the knowledge graph based on the machine learning model by changing one or more identified neighborhoods corresponding to one or more homes in the home location data.