IP Library › Granted Patent US 12,339,861
Granted Patent B2
US 12,339,861 · App. 18/532,366 · Granted Jun 24, 2025

Identity resolution in knowledge graph databases

Inventors: David Newman (Walnut Creek, CA); Omar B. Khan (Richmond, VA); Nikolai Anisimov (Concord, CA)
Assignee: Wells Fargo Bank, N.A.
G06F16/248G06F16/258
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 12,339,861
App. No.
18/532,366
Granted
Jun 24, 2025
Kind
B2
Abstract

A method may include presenting a user interface on a computing device, the user interface including: an input element configured to receive an input of a search concept; a similar concept selection element; and a concept comparison portion; executing a similarity search in a vector-space representation of a knowledge graph using the input; populating the similar concept selection element with a set of a similar concepts based on a result of the executed similarity search; receiving a selection of a comparison concept of the set of similar concepts from the similar concept selection element; generating a predicate comparison visualization in the concept comparison portion based on predicates in the knowledge graph of the comparison concept and the search concept; and presenting the predicate comparison visualization in the concept comparison portion.

Claims (73)

1. A method comprising:

presenting an input element configured to receive an input of a search concept;

receiving an input of the search concept from the input element;

using the input of the search concept, executing a search of a knowledge graph storing subject, object, and predicate triples;

in response to the executing, presenting a set of similar concepts, the set of similar concepts corresponding to a set of subjects in the knowledge graph;

receiving a selection of a comparison concept of the set of similar concepts;

in response to receiving the selection, generating a predicate comparison visualization based on predicates of triples stored in the knowledge graph of the comparison concept and the search concept, wherein generating the predicate comparison visualization includes:

retrieving values of a subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the search concept;

retrieving values of the subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the comparison concept; and

for each respective predicate in the subset of the predicates:

selecting a similarity algorithm of a plurality of similarity algorithms based on a type of property associated with the respective predicate;

executing the similarity algorithm using the value of the respective predicate for the search concept compared with the value of the respective predicate for the comparison concept as inputs to the similarity algorithm;

receiving an output value of the similarity algorithm for the respective predicate; and

adding the value of the respective predicate for the comparison concept, the value of the respective predicate for the search concept, and the output value of the similarity algorithm for the respective predicate to the predicate comparison visualization; and

presenting the predicate comparison visualization.

2. The method of claim 1 , wherein the predicate comparison visualization is a table with a first column displaying the value of the respective predicate for the search concept, a second column for the value of the respective predicate for the comparison concept, and a third column for the output value of the similarity algorithm for the respective predicate.

3. The method of claim 2 , wherein the table includes a fourth column with identifiers of predicates in the knowledge graph.

4. The method of claim 1 , wherein the predicate comparison visualization is a graph visualization.

5. The method of claim 4 , wherein generating the predicate comparison visualization includes:

generating a node for the comparison concept; and

generating a node for the search concept.

6. The method of claim 5 , wherein generating the predicate comparison visualization includes:

connecting the node for the comparison concept to a predicate node labeled with an identifier of a predicate.

7. The method of claim 6 , wherein generating the predicate comparison visualization includes:

generating a similarity value node, wherein the similarity value node includes the output value of the similarity algorithm for the respective predicate.

8. The method of claim 7 , wherein an edge between the similarity value node and the predicate node is labeled with value of the respective predicate for the search concept.

9. A non-transitory computer-readable medium comprising instructions, which when executed by a processing unit, configure the processing unit to perform operations comprising:

presenting an input element configured to receive an input of a search concept;

receiving an input of the search concept from the input element:

using the input of the search concept, executing a search of a knowledge graph storing subject, object, and predicate triples;

in response to the executing, presenting a set of similar concepts, the set of similar concepts corresponding to a set of subjects in the knowledge graph;

receiving a selection of a comparison concept of the set of similar concepts;

in response to receiving the selection, generating a predicate comparison visualization based on predicates of triples stored in the knowledge graph of the comparison concept and the search concept, wherein generating the predicate comparison visualization includes:

retrieving values of a subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the search concept;

retrieving values of the subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the comparison concept;

for each respective predicate in the subset of the predicates:

selecting a similarity algorithm of a plurality of similarity algorithms based on a type of property associated with the respective predicate;

executing the similarity algorithm using the value of the respective predicate for the search concept compared with the value of the respective predicate for the comparison concept as inputs to the similarity algorithm;

receiving an output value of the similarity algorithm for the respective predicate; and

adding the value of the respective predicate for the comparison concept, the value of the respective predicate for the search concept, and the output value of the similarity algorithm for the respective predicate to the predicate comparison visualization; and

presenting the predicate comparison visualization.

10. The non-transitory computer-readable medium of claim 9 , wherein the predicate comparison visualization is a table with a first column displaying the value of the respective predicate for the search concept, a second column for the value of the respective predicate for the comparison concept, and a third column for the output value of the similarity algorithm for the respective predicate.

11. The non-transitory computer-readable medium of claim 10 , wherein the table includes a fourth column with identifiers of predicates in the knowledge graph.

12. The non-transitory computer-readable medium of claim 9 , wherein the predicate comparison visualization is a graph visualization.

13. The non-transitory computer-readable medium of claim 12 , wherein generating the predicate comparison visualization includes:

generating a node for the comparison concept; and

generating a node for the search concept.

14. The non-transitory computer-readable medium of claim 13 , wherein generating the predicate comparison visualization includes:

connecting the node for the comparison concept to a predicate node labeled with an identifier of a predicate.

15. The non-transitory computer-readable medium of claim 14 , wherein generating the predicate comparison visualization includes:

generating a similarity value node, wherein the similarity value node includes the output value of the similarity algorithm for the respective predicate.

16. The non-transitory computer-readable medium of claim 15 ,

wherein an edge between the similarity value node and the predicate node is labeled with value of the respective predicate for the search concept.

17. A system comprising:

at least one processor; and

a storage device comprising instructions, which when executed by the at least one processor, configure the at least one processor to perform operations comprising:

presenting an input element configured to receive an input of a search concept;

receiving an input of the search concept from the input element;

using the input of the search concept, executing a search of a knowledge graph storing subject, object, and predicate triples;

in response to the executing, presenting a set of similar concepts, the set of similar concepts corresponding to a set of subjects in the knowledge graph;

receiving a selection of a comparison concept of the set of similar concepts;

in response to receiving the selection, generating a predicate comparison visualization based on predicates of triples stored in the knowledge graph of the comparison concept and the search concept, wherein generating the predicate comparison visualization includes:

retrieving values of a subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the search concept;

retrieving values of the subset of the predicates in the knowledge graph from triples stored in the knowledge graph of the comparison concept;

for each respective predicate in the subset of the predicates:

selecting a similarity algorithm of a plurality of similarity algorithms based on a type of property associated with the respective predicate;

executing the similarity algorithm using the value of the respective predicate for the search concept compared with the value of the respective predicate for the comparison concept as inputs to the similarity algorithm;

receiving an output value of the similarity algorithm for the respective predicate; and

adding the value of the respective predicate for the comparison concept, the value of the respective predicate for the search concept, and the output value of the similarity algorithm for the respective predicate to the predicate comparison visualization; and

presenting the predicate comparison visualization.

18. The system of claim 17 , wherein the predicate comparison visualization is a table with a first column displaying the value of the respective predicate for the search concept, a second column for the value of the respective predicate for the comparison concept, and a third column for the output value of the similarity algorithm for the respective predicate.

19. The system of claim 18 , wherein the table includes a fourth column with identifiers of predicates in the knowledge graph.

20. The system of claim 17 , wherein the predicate comparison visualization is a graph visualization.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE SPELLING OF INVENTOR ANISIMOV'S LAST NAME AS PREVIOUSLY RECORDED ON REEL 66045 FRAME 500. ASSIGNOR(S) HEREBY CONFIRMS THE THE FILING OF THE ASSIGNMENT. Recorded May 23, 2025
From: NEWMAN, DAVID; KHAN, OMAR B; ANISIMOV, NIKOLAI
To: WELLS FARGO BANK, N.A.
Reel/Frame 071352/0113 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 8, 2024
From: NEWMAN, DAVID; KHAN, OMAR B; ANNISSIMOV, NIKOLAI
To: WELLS FARGO BANK, N.A.
Reel/Frame 066045/0500 →
Continuity (2)
Continuation 17661158 · Apr 28, 2022
Related Publication 20240104112A1 · Mar 28, 2024
References Cited (76)
US 7630978B2 · Li et al. · 2009 [cited by applicant]
US 7840577B2 · Ortega et al. · 2010 [cited by applicant]
US 9189742B2 · London · 2015 [cited by applicant]
US 9535902B1 · Michalak et al. · 2017 [cited by applicant]
US 9766983B2 · Reddy et al. · 2017 [cited by applicant]
US 9779147B1 · Sherman et al. · 2017 [cited by applicant]
US 10348658B2 · Rodriguez et al. · 2019 [cited by applicant]
US 10628490B2 · Yakout et al. · 2020 [cited by applicant]
US 10733619B1 · Newman · 2020 [cited by applicant]
US 10740541B2 · Zambre et al. · 2020 [cited by applicant]
US 10762118B2 · Tripathi et al. · 2020 [cited by applicant]
US 10769142B2 · Chen · 2020 [cited by applicant]
US 10936969B2 · Patel et al. · 2021 [cited by applicant]
US 10951763B2 · Copeland · 2021 [cited by applicant]
US 11106736B1 · Newman et al. · 2021 [cited by applicant]
US 11200376B2 · Bull et al. · 2021 [cited by applicant]
US 11436270B2 · Skupin et al. · 2022 [cited by applicant]
US 11580127B1 · Newman · 2023 [cited by applicant]
US 11768837B1 · Newman et al. · 2023 [cited by applicant]
US 11880379B1 · Newman et al. · 2024 [cited by applicant]
US 12072918B1 · Newman · 2024 [cited by examiner]
US 20110307819A1 · Vadlamani et al. · 2011 [cited by applicant]
US 20140358906A1 · Behzadi et al. · 2014 [cited by applicant]
US 20150178273A1 · Hakkani-tur et al. · 2015 [cited by applicant]
US 20160027197A1 · Beckett et al. · 2016 [cited by applicant]
US 20170161619A1 · Franceschini et al. · 2017 [cited by applicant]
US 20170228372A1 · Moreno et al. · 2017 [cited by applicant]
US 20180129369A1 · Kim et al. · 2018 [cited by applicant]
US 20180150759A1 · Nitta et al. · 2018 [cited by applicant]
US 20180300409A9 · Dingwall et al. · 2018 [cited by applicant]
US 20180373791A1 · Yen et al. · 2018 [cited by applicant]
US 20190087732A1 · Park · 2019 [cited by examiner]
US 20190179917A1 · Agrawal et al. · 2019 [cited by applicant]
US 20190205475A1 · Ulfelder, Jr. et al. · 2019 [cited by applicant]
US 20190236460A1 · Jagota et al. · 2019 [cited by applicant]
US 20200117857A1 · Gnanasambandam et al. · 2020 [cited by applicant]
US 20200151392A1 · Crabtree et al. · 2020 [cited by applicant]
US 20200242140A1 · Xu et al. · 2020 [cited by applicant]
US 20200272662A1 · Markovic et al. · 2020 [cited by applicant]
US 20200322361A1 · Ravindra et al. · 2020 [cited by applicant]
US 20200349324A1 · Ostby et al. · 2020 [cited by applicant]
US 20200401593A1 · Panuganty et al. · 2020 [cited by applicant]
US 20210081499A1 · Rakshit et al. · 2021 [cited by applicant]
US 20210279420A1 · Jain et al. · 2021 [cited by applicant]
US 20220101153A1 · Hubauer · 2022 [cited by examiner]
US 20230081891A1 · Kulkarni et al. · 2023 [cited by applicant]
US 20230385291A1 · Newman et al. · 2023 [cited by applicant]
WO 2019172849 · 2019 [cited by applicant]
WO 2020162884 · 2020 [cited by applicant]
U.S. Appl. No. 17/646,228 U.S. Pat. No. 11,768,837, filed Dec. 28, 2021, Semantic Entity Search Using Vector Space. [cited by applicant]
U.S. Appl. No. 17/661,158 U.S. Pat. No. 11,880,379, filed Apr. 28, 2022, Identity Resolution in Knowledge Graph Databases. [cited by applicant]
U.S. Appl. No. 18/365,075, filed Aug. 3, 2023, Semantic Entity Search Using Vector Space. [cited by applicant]
“U.S. Appl. No. 18/365,075, Non Final Office Action mailed Apr. 22, 2024”, 10 pgs. [cited by applicant]
“U.S. Appl. No. 18/365,075, Response filed Jun. 13, 2024 to Non Final Office Action mailed Apr. 22, 2024”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 18/365,075, Notice of Allowance mailed Jul. 17, 2024”, 5 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Non Final Office Action mailed Jan. 7, 2021”10 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Response filed Apr. 5, 2021 to Non Final Office Action mailed Jan. 7, 2021”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Final Office Action mailed Jul. 7, 2021” 12 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Response filed Sep. 7, 2021 to Final Office Action mailed Jul. 7, 2021”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Advisory Action mailed Sep. 27, 2021”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Non Final Office Action mailed Dec. 9, 2021” 13 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Response filed Jun. 8, 2022 to Non Final Office Action mailed Dec. 9, 2021” 8 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Final Office Action mailed Jun. 28, 2022”, 14 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Response filed Sep. 28, 2022 to Final Office Action mailed Jun. 28, 2022”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 16/230,879, Notice of Allowance mailed Oct. 12, 2022”, 6 pgs. [cited by applicant]
“U.S. Appl. No. 18/168,267, Preliminary Amendment filed Apr. 4, 2023”, 7 pgs. [cited by applicant]
“U.S. Appl. No. 17/646,228, Notice of Allowance mailed May 4, 2023”, 14 pgs. [cited by applicant]
“U.S. Appl. No. 17/646,228, Corrected Notice of Allowability mailed May 16, 2023”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 17/661,158, Non Final Office Action mailed May 23, 2023”, 16 pgs. [cited by applicant]
“U.S. Appl. No. 17/646,228, 312 Amendment filed Jun. 12, 2023”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 17/646,228, PTO Response to Rule 312 Communication mailed Jul. 28, 2023”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 17/661,158, Examiner Interview Summary mailed Aug. 10, 2023”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 17/661,158, Response filed Sep. 25, 2023 to Non Final Office Action mailed May 23, 2023”, 10 pgs. [cited by applicant]
“U.S. Appl. No. 17/661,158, Notice of Allowance mailed Oct. 11, 2023”, 8 pgs. [cited by applicant]
Kasyanov, Victor, “Information Visualization on the Base of Hierachical Graphs”, Matematichki Bilten vol. 39, No. 1, [Online]. Retrieved from the Internet: URL: http: im-pmf.weebly.com uploads 5 8 9 8 58988609kasyanov-k… [cited by applicant]
Racz, Gabor, “Visualization of Semantic Data Based on Selected Predicates”, Part of the Lecture Notes in Computer Science book series (LNCS, vol. 8615), (Aug. 17, 2014), 22 pgs. [cited by applicant]