Knowledge Graph Systems for Loan Data Aggregation and Anomaly Detection

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted patent US12591788B1 to Federal Home Loan Mortgage Corporation (Freddie Mac) for knowledge graph systems that aggregate loan data, extract property attributes including loan amounts and appraisal sources, and detect statistical anomalies in valuation distributions. The patent covers methods for generating knowledge graph data structures from aggregated mortgage-related entity data with 20 total claims.

View original document View source feed page

What changed

USPTO issued Patent No. US12591788B1 to Freddie Mac on March 31, 2026, covering systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis in mortgage data contexts. The patent describes processors and databases that aggregate data across multiple entities, extract attribute information including loan amounts, property values, and appraisal sources, generate statistical distributions of appraisal attributes, and detect anomalies through comparative analysis of distributions.

This patent grant represents intellectual property protection for Freddie Mac's technology with no immediate compliance obligations for other entities. Financial institutions and technology companies developing knowledge graph applications for loan or property valuation analysis should be aware that Freddie Mac holds patent rights in this area, potentially affecting future product development strategies in automated valuation and mortgage data analytics.

Source document (simplified)

← USPTO Patent Grants

Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis

Grant US12591788B1 Kind: B1 Mar 31, 2026

Assignee

Federal Home Loan Mortgage Corporation (Freddie Mac)

Inventors

Yuang Tang, Fabio Quijada, Dylan Nielson

Abstract

This disclosure relates to knowledge generation and implementation. A knowledge graph system comprises at least one processor, at least one database communicatively connected to the at least one processor, and a memory storing executable instructions. When executed, the instructions cause the at least one processor to aggregate data associated with a plurality of entities, the aggregated data reflecting one or more relationships between two or more of the plurality of entities. Attribute data identifying loan amounts, property values, and appraisal sources may be extracted from the aggregated data. A knowledge graph data structure may be generated having a plurality of subject notes corresponding to the extracted attribute information. Statistical distributions of attributes associated with one or more appraisal sources may be generated and an anomaly in a first statistical distribution may be detected based on a comparison of the first statistical distribution with a second statistical distribution.