IP Library › Granted Patent US 12,632,910
Granted Patent B2
US 12,632,910 · App. 18/670,606 · Granted May 19, 2026

Artificial intelligence-based block embedding

Inventors: Kien Trong Trinh (San Diego, CA); Wei Geng (San Diego, CA); Bin He (Philadelphia, PA)
Assignee: CoreLogic Solutions, LLC
G06Q50/16G06N20/00G06Q30/0278
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,632,910
App. No.
18/670,606
Granted
May 19, 2026
Kind
B2
Abstract

A computer system and associated processes for grouping similar real estate properties into contiguous neighborhoods and generating neighborhood-specific models capable of estimating property values within their neighborhoods. An artificial intelligence system directed to using a graph neural network framework to identify relationships between different parcel groups based on similar property features and embed the parcel groups into low dimensional space vectors. The method can include generating a graph and features relevant to the parcel groups that can train an embedding function that generate an embedding vector for each parcel group in a geographic unit grouping, such as a census tract. Embedding vectors of two or more parcel groups can then be compared to each other to determine whether the parcel groups are similar or to determine a housing valuation of a parcel group.

Claims (63)

1 . A computer-implemented method for embedding parcel groups, the computer-implemented method comprising:

obtaining a geographic unit grouping, wherein the geographic unit grouping comprises at least two parcel groups including a first parcel group and a second parcel group, wherein each of the first parcel group and the second parcel group comprises at least one parcel;

obtaining property-level data for the first and second parcel groups in the geographic unit grouping;

generating a graph model using the property-level data, wherein the graph model comprises one or more polygons for each of the first and second parcel groups that indicate a relationship between a geographic area of the first parcel group and a geographic area of the second parcel group;

generating property features for each of the first and second parcel groups using the property-level data;

training an embedding function to generate an embedding vector that include a number of dimensions that is less than a number of the at least two parcel groups based on inputting the property features and the one or more polygons of the graph model into a neighbor predicting artificial intelligence model, wherein the neighbor predicting artificial intelligence model is trained to determine a relationship between the at least two parcel groups, the embedding vector comprising a unique identification of a parcel group based on the relationship between the at least two parcel groups;

generating a first embedding vector of the first parcel group and a second embedding vector for the second parcel group using the trained embedding function;

applying the first and second embedding vectors as an input to an artificial intelligence model, wherein application of the first and second embedding vectors as the input to the artificial intelligence model causes the artificial intelligence model to produce an output; and

generating an outcome for the first parcel group based on the output.

2 . The method of claim 1 , wherein the property-level data comprises property data and census data.

3 . The method of claim 1 , wherein generating the property features for each of the first and second parcel groups comprises an aggregation of parcel features for each of the at least one parcels in the first and second parcel groups respectively.

4 . The method of claim 1 , further comprising generating a visualization of the first and second embedding vectors.

5 . The method of claim 1 , wherein the artificial intelligence model comprises one of an automated valuation model, a rental valuation model, or a neighborhood recommendation model.

6 . The method of claim 1 , wherein the outcome comprises one of a housing value, a rental value, or a recommendation for the first parcel group.

7 . The method of claim 1 , wherein training the embedding function comprises:

obtaining the neighbor predicting artificial intelligence model;

generating the embedding function using the property features and the one or more polygons of the graph model as an input to train the neighbor predicting artificial intelligence model; and

training the embedding function using the neighbor predicting intelligence model and the property features to generate the trained embedding function;

wherein generating the first embedding vector using the trained embedding function comprises:

determining a neighbor score between the first and second parcel groups corresponding to the property features using the neighbor predicting artificial intelligence model; and

inputting into the trained embedding function the property features of the first parcel group and, if the neighbor score meets a neighbor threshold, further inputting into the trained embedding function the property features of the second parcel group.

8 . The method of claim 7 , wherein determining the neighbor score further comprises weighing the property features unequally.

9 . The method of claim 1 , wherein obtaining the geographic unit grouping further comprises encoding each of the first and second parcel groups.

10 . The method of claim 1 , wherein the embedding vector comprise a dimensionally reduced vector of the first and second parcel groups, and wherein a dimension is encoded with the property feature of the first and second parcel group.

11 . The method of claim 10 , wherein the number of dimensions for each of the embedding vector comprises 32-dimensions.

12 . The method of claim 1 , further comprising:

generating a plurality of embedding vectors from the at least two parcel groups using the trained embedding function; and

training the artificial intelligence model using the plurality of embedding vectors prior to generating the first embedding vector and the second embedding vector.

13 . A system for parcel group embedding, the system comprising:

memory that stores computer-executable instructions; and

a processor in communication with the memory, wherein the computer-executable instructions, when executed by the processor, cause the processor to:

obtain a geographic unit grouping, wherein the geographic unit grouping comprises at least two parcel groups including a first parcel group and a second parcel group, wherein each of the first parcel group and the second parcel group comprises at least one parcel;

obtain property-level data for the first and second parcel groups in the geographic unit grouping;

generate a graph model using the property-level data, wherein the graph model comprises one or more polygons for each of the first and second parcel groups that indicate a relationship between a geographic area of the first parcel group and a geographic area of the second parcel group;

generate property features for each of the first and second parcel groups using the property-level data;

train an embedding function to generate an embedding vector that include a number of dimensions that are less than a number of the at least two parcel groups based on inputting the property features and the one or more polygons of the graph model into a neighbor predicting artificial intelligence model, wherein the neighbor predicting artificial intelligence model is trained to determine a relationship between the at least two parcel groups, the embedding vector comprising a unique identification of a parcel group based on the relationship between the at least two parcel groups;

generate a first embedding vector for the first parcel group and a second embedding vector for the second parcel group using the trained embedding function;

apply the first and second embedding vectors as an input to an artificial intelligence model, wherein application of the first and second embedding vectors as the input to the artificial intelligence model causes the artificial intelligence model to produce an output; and

generate an outcome for the first parcel group based on the output.

14 . The system of claim 13 , wherein the property-level data comprises property data and census data.

15 . The system of claim 13 , wherein the property features for each of the first and second parcel groups comprises an aggregation of parcel features for each of the at least one parcels in the first and second parcel groups respectively.

16 . The system of claim 13 , wherein the computer-executable instructions, when executed, further cause the processor to generate a visualization of the first and second embedding vectors.

17 . The system of claim 13 , wherein the artificial intelligence model comprises one of an automated valuation model, a rental valuation model, or a neighborhood recommendation model.

18 . The system of claim 13 , wherein the outcome comprises one of a housing value, a rental value, or a recommendation for the first parcel group.

19 . The system of claim 13 , wherein the computer-executable instructions, when executed, further cause the processor to train the embedding function by:

obtaining the neighbor predicting artificial intelligence model;

generating the embedding function using the property features and the one or more polygons of the graph model as an input to train the neighbor predicting artificial intelligence model; and

training the embedding function using the neighbor predicting intelligence model and the property features to generate the trained embedding function;

wherein the computer-executable instructions, when executed, further cause the processor to generate the first embedding vector using the trained embedding function by:

determining a neighbor score between the first and second parcel groups corresponding to the property features using the neighbor predicting artificial intelligence model; and

inputting into the trained embedding function the property features of the first parcel group and, if the neighbor score meets a neighbor threshold, further inputting into the trained embedding function the property features of the second parcel group.

20 . The system of claim 13 , wherein the computer-executable instructions, when executed, further cause the processor to obtain an encoded identification of the at least one parcels.

21 . The system of claim 13 , wherein the embedding vector comprise a dimensionally reduced vector of the first and second parcel groups, and wherein a dimension is encoded with the property feature of the first and second parcel group.

22 . The system of claim 21 , wherein each of the embedding vector comprises 32-dimensions.

23 . A non-transitory, computer-readable medium comprising computer-executable instructions for embedding parcel groups, wherein the computer-executable instructions, when executed by a computer system, cause the computer system to:

obtain a geographic unit grouping, wherein the geographic unit grouping comprises at least two parcel groups including a first parcel group and a second parcel group, wherein each of the first parcel group and the second parcel group comprises at least one parcel;

obtain property-level data for the first and second parcel groups in the geographic unit grouping;

generate a graph model using the property-level data, wherein the graph model comprises one or more polygons for each of the first and second parcel groups that indicate a relationship between a geographic area of the first parcel group and a geographic area of the second parcel group;

generate property features for each of the first and second parcel groups using the property-level data;

train an embedding function to generate an embedding vector that include a number of dimensions that are less than a number of the at least two parcel groups based on inputting the property features and the one or more polygons of the graph model into a neighbor predicting artificial intelligence model, wherein the neighbor predicting artificial intelligence model is trained to determine a relationship between the at least two parcel groups, the embedding vector comprising a unique identification of a parcel group based on the relationship between the at least two parcel groups;

generate a first embedding vector of the first parcel group and a second embedding vector for the second parcel group using the trained embedding function;

apply the first and second embedding vectors as an input to an artificial intelligence model, wherein application of the first and second embedding vectors as the input to the artificial intelligence model causes the artificial intelligence model to produce an output; and

generate an outcome for the first parcel group based on the output.

Assignments (4)
SECOND LIEN PATENT SECURITY AGREEMENT Recorded Jul 28, 2026
From: CORELOGIC SOLUTIONS, LLC , AS A GRANTOR
To: U.S. BANK TRUST COMPANY, NATIONAL ASSOCIATION, AS SECOND LIEN NOTES COLLATERAL AGENT
Reel/Frame 076077/0224 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded Jul 28, 2026
From: CORELOGIC SOLUTIONS, LLC, AS A GRANTOR
To: U.S. BANK TRUST COMPANY, NATIONAL ASSOCIATION, AS FIRST LIEN NOTES COLLATERAL AGENT
Reel/Frame 076077/0305 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded Jul 28, 2026
From: CORELOGIC SOLUTIONS, LLC, AS GRANTOR
To: JPMORGAN CHASE BANK, N.A., AS FIRST LIEN COLLATERAL AGENT
Reel/Frame 076097/0647 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 26, 2024
From: TRINH, KIEN TRONG; GENG, WEI; HE, BIN
To: CORELOGIC SOLUTIONS, LLC
Reel/Frame 067850/0533 →
Continuity (2)
Provisional Application 63469299 · May 26, 2023
Related Publication 20240394813A1 · Nov 28, 2024
References Cited (89)
US 5193185A · Lanter · 1993 [cited by applicant]
US 5361201A · Jost · 1994 [cited by examiner]
US 5857174A · Dugan · 1999 [cited by examiner]
US 7890509B1 · Pearcy et al. · 2011 [cited by applicant]
US 8732219B1 · Ferries et al. · 2014 [cited by applicant]
US 10248731B1 · Brouwer et al. · 2019 [cited by applicant]
US 10303816B2 · Nakazawa · 2019 [cited by applicant]
US 10496678B1 · Tang · 2019 [cited by applicant]
US 10521943B1 · Phillips et al. · 2019 [cited by applicant]
US 10726509B1 · Cannon et al. · 2020 [cited by applicant]
US 11301774B2 · Garcia Duran · 2022 [cited by examiner]
US 11373233B2 · Pande · 2022 [cited by examiner]
US 11373257B1 · Guo et al. · 2022 [cited by applicant]
US 11657633B1 · Vandivere · 2023 [cited by applicant]
US 11971263B1 · Malshe et al. · 2024 [cited by applicant]
US 12461951B1 · Trinh et al. · 2025 [cited by applicant]
US 20030158668A1 · Anderson · 2003 [cited by applicant]
US 20030158801A1 · Chuah · 2003 [cited by applicant]
US 20050288957A1 · Eraker et al. · 2005 [cited by applicant]
US 20090132469A1 · White et al. · 2009 [cited by applicant]
US 20130328882A1 · Pirwani et al. · 2013 [cited by applicant]
US 20140365470A1 · Diamond et al. · 2014 [cited by applicant]
US 20150120455A1 · Mcdevitt et al. · 2015 [cited by applicant]
US 20150186951A1 · Wilson et al. · 2015 [cited by applicant]
US 20150213160A1 · Bright et al. · 2015 [cited by applicant]
US 20150242747A1 · Packes · 2015 [cited by examiner]
US 20160125338A1 · Serageldin et al. · 2016 [cited by applicant]
US 20160259841A1 · Andrew et al. · 2016 [cited by applicant]
US 20160299639A1 · Adams et al. · 2016 [cited by applicant]
US 20160379388A1 · Rasco et al. · 2016 [cited by applicant]
US 20170287080A1 · Aruswamy et al. · 2017 [cited by applicant]
US 20170316324A1 · Barrett et al. · 2017 [cited by applicant]
US 20170323028A1 · Jonker et al. · 2017 [cited by applicant]
US 20180121577A1 · Taylor et al. · 2018 [cited by applicant]
US 20180158158A1 · Coogan-Pushner · 2018 [cited by applicant]
US 20190050491A1 · Mask et al. · 2019 [cited by applicant]
US 20190272669A1 · Esposito et al. · 2019 [cited by applicant]
US 20200380086A1 · Ivanov et al. · 2020 [cited by applicant]
US 20200402116A1 · Avrahami · 2020 [cited by examiner]
US 20210019325A1 · Edge · 2021 [cited by examiner]
US 20210037394A1 · Wainer et al. · 2021 [cited by applicant]
US 20210103998A1 · Rose · 2021 [cited by examiner]
US 20210125271A1 · O'Moore · 2021 [cited by examiner]
US 20210256572A1 · Rute et al. · 2021 [cited by applicant]
US 20210325891A1 · Young et al. · 2021 [cited by applicant]
US 20210398227A1 · Hayward · 2021 [cited by examiner]
US 20220084079A1 · Stewart · 2022 [cited by examiner]
US 20220180169A1 · Gore · 2022 [cited by examiner]
US 20220222758A1 · Beckman · 2022 [cited by examiner]
US 20220292330A1 · Ma · 2022 [cited by examiner]
US 20220292543A1 · Henderson · 2022 [cited by applicant]
US 20220327643A1 · Law et al. · 2022 [cited by applicant]
US 20220335307A1 · Wang et al. · 2022 [cited by applicant]
US 20220335353A1 · Copley et al. · 2022 [cited by applicant]
US 20220383417A1 · Cummings · 2022 [cited by applicant]
US 20230029218A1 · Bhamidipaty et al. · 2023 [cited by applicant]
US 20230119132A1 · Cebulski et al. · 2023 [cited by applicant]
US 20230153931A1 · Lee · 2023 [cited by applicant]
US 20230297834A1 · Chigogidze · 2023 [cited by examiner]
US 20230385738A1 · Lobell et al. · 2023 [cited by applicant]
US 20240112257A1 · Sharma · 2024 [cited by examiner]
US 20240273637A1 · Gibson · 2024 [cited by examiner]
US 20250200618A1 · Trinh et al. · 2025 [cited by applicant]
US 20250292291A1 · Humphries · 2025 [cited by examiner]
CA 3165715A1 · 2021 [cited by applicant]
CN 101419623A · 2009 [cited by applicant]
CN 113627977A · 2021 [cited by applicant]
CN 115018215A · 2022 [cited by applicant]
CN 115271825A · 2022 [cited by examiner]
WO WO2023141579A1 · 2023 [cited by examiner]
WO 2024249178A1 · 2024 [cited by applicant]
WO 2025136982A1 · 2025 [cited by applicant]
Translation of Foreign document CN115271825A, retrieved from https://worldwide.espacenet.com/patent/search/family/083751482/publication/CN115271825A (Year: 2022). [cited by examiner]
Zhang et al., “MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal,” In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD '21), 2021,… [cited by examiner]
Yu et al., “Research on real estate pricing methods based on data mining and machine learning,” Neural Comput & Applic 33, 3925-3937, 2021, https://doi.org/10.1007/s00521-020-05469-3 (Year: 2021). [cited by examiner]
B. Trawiński et al., “Comparison of expert algorithms with machine learning models for real estate appraisal,” 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Gdynia, … [cited by examiner]
Lin, Sandgi. “Home Embeddings for Similar Home Recommendations.” https://www.zillow.com/tech/embedding-similar-home-recommendation/ Accessed May 21, 2024. [cited by applicant]
“Knowledge graph embedding,” Wikipedia, Oct. 25, 2023, 9 pages. URL: https://en.wikipedia.org/w/index.php?title=Knowledge_graph_embedding&oldid=1181784194. [cited by applicant]
Han, S., et al., “Improving Real Estate Appraisal with POI Integration and Areal Embedding,” arXiv.org, Artificial Intelligence (cs.AI), Nov. 20, 2023, 13 pages. [cited by applicant]
International Preliminary Report on Patentability for PCT Application No. PCT/US2024/030350, mailed Dec. 11, 2025. [cited by applicant]
International Search Report and Written Opinion for PCT Application No. PCT/US24/030350, mailed Oct. 16, 2024. [cited by applicant]
International Search Report and Written Opinion for PCT Application No. PCT/US24/060576, mailed Feb. 12, 2025. [cited by applicant]
Li, C.C., et al., “Look Around! A Neighbor Relation Graph Learning Framework for Real Estate Appraisal,” arXiv.org, Machine Learning (cs.LG), Dec. 23, 2022, 10 pages. [cited by applicant]
Lisowski, P. et al., “Topological Model of Selected Cadastral Structures Visualized in Form of Graphs”, Geomatics and Environmental Engineering, 2017, vol. 11(4), pp. 51-63. [cited by applicant]
Rao, B., et al., “An approach to merging of two community subgraphs to form a community graph using graph mining techniques,” IEEE International Conference on Computational Intelligence and Computing Research, Dec. 18, … [cited by applicant]
Wu, P., et al., “Urban parcel grouping method based on urban form and functional connectivity characterisation,” International Journal of Geo-Information, Jun. 2019, vol. 8, 27 pages. [cited by applicant]
Yang, A., et al., “Graph Convolutional Network-Based Model for Megacity Real Estate Valuation,” IEEE Access, vol. 10, Sep. 2022, pp. 104811-104828. [cited by applicant]
Ye, X., et al., “Automating land parcel classification for neighborhood-scale urban analysis,” International Journal of Digital Earth, 2019, vol. 12, pp. 1396-1405. [cited by applicant]
Zhang, W., et al., “MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal,” arXiv.org, Machine Learning (cs.LG), Aug. 2, 2021, 11 pages. [cited by applicant]