IP Library › Granted Patent US 12675706

Granted Patent B2

US 12675706 · App. 17/653,788 · Granted Jul 7, 2026

Systems and methods for building a unified asset graph

Inventors: Ryan Eavy (Chicago, IL); Tayo Ibikunle (Haverford, PA)

Assignee: JPMORGAN CHASE BANK, N.A.

G06N5/02 G06F16/9024

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 12675706
App. No.: 17/653,788
Granted: Jul 7, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Systems and methods for building a unified asset graph are disclosed. In one aspect, a method includes determining an intended state and a functional state of a plurality of evaluated architectures of an evaluating organization; generating a knowledge graph, wherein the knowledge graph includes an intended state dimension and a functional state dimension, and wherein the intended state dimension is based on the determined intended state of the plurality of evaluated architectures and the functional state dimension is based on the determined functional state of the plurality of evaluated architectures; and generating a social knowledge dimension of the knowledge graph, wherein the social dimension is based on one or more architecture nodes included in the knowledge graph, and wherein values of attribute nodes of the social knowledge dimension are at least partially based on user-generated data received by the knowledge graph.

Claims (46)

1 . A method for building and querying a knowledge graph executed by at least one processor of a server system comprising a memory comprising instructions, the instructions comprising steps of:

determining an intended state and a functional state of a plurality of evaluated architectures of an evaluating organization;

generating a knowledge graph, wherein the knowledge graph includes an intended state dimension and a functional state dimension, and wherein the intended state dimension is based on the determined intended state of the plurality of evaluated architectures and the functional state dimension is based on the determined functional state of the plurality of evaluated architectures; and

generating a social knowledge dimension of the knowledge graph, wherein the social dimension is based on one or more architecture nodes included in the knowledge graph, and wherein values of attribute nodes of the social knowledge dimension are at least partially based on user-generated data received by the knowledge graph,

wherein the knowledge graph is stored in a graph database, and the generating and querying steps comprise automatically integrating user-generated data into the knowledge graph using a machine learning model configured to classify and associate the user-generated data with corresponding architecture nodes by associating determined sentence parts within the user-generated data as relationships, and wherein querying the knowledge graph comprises receiving, by the server system, a query in natural language, processing the query using a natural language processing engine to generate graph query parameters, and executing the query against the graph database to retrieve results, wherein the results are provided to a user via an interface.

2 . The method of claim 1 , wherein the user-generated data is received via a user interface of the knowledge graph.

3 . The method of claim 2 , wherein the user-generated data includes a self-identification from a user as a user of the one or more architecture nodes.

4 . The method of claim 2 , wherein the user-generated data includes a comment regarding an evaluated architecture represented by the one or more architecture nodes.

5 . The method of claim 2 , wherein the user-generated data includes a quality score regarding an evaluated architecture represented by the one or more architecture nodes.

6 . The method of claim 1 , comprising:

receiving, at a query engine, a natural language query;

processing the natural language query with a natural language query processing engine;

generating, as a result of the processing the natural language query with the natural language processing engine, a plurality of graph properties;

querying the knowledge graph using the plurality of graph properties as parameters; and

displaying the results of the querying through the interface.

7 . The method of claim 6 , comprising:

formatting, by the query engine, the results of the querying into a natural language format.

8 . The method of claim 7 , wherein the natural language query is associated with a confidence score.

9 . The method of claim 8 , comprising,

receiving positive feedback from a submitter of the natural language query with respect to an accuracy of the results of the querying.

10 . The method of claim 9 , comprising:

raising the confidence score based on the positive feedback.

11 . A system for building and querying a knowledge graph comprising at least one server including a processor and a memory, wherein the at least one server is configured for operative communication on a technology infrastructure of an evaluating organization, and wherein instructions stored on the memory instruct the processor to:

determine an intended state and a functional state of a plurality of evaluated architectures of an evaluating organization;

generate a knowledge graph, wherein the knowledge graph includes an intended state dimension and a functional state dimension, and wherein the intended state dimension is based on the determined intended state of the plurality of evaluated architectures and the functional state dimension is based on the determined functional state of the plurality of evaluated architectures; and

generate a social knowledge dimension of the knowledge graph, wherein the social dimension is based on one or more architecture nodes included in the knowledge graph, and wherein values of attribute nodes of the social knowledge dimension are at least partially based on user-generated data received by the knowledge graph, wherein the knowledge graph is stored in a graph database, and the generating and querying steps comprise automatically integrating user-generated data into the knowledge graph using a machine learning model configured to classify and associate the user-generated data with corresponding architecture nodes by associating determined sentence parts within the user-generated data as relationships, and wherein querying the knowledge graph comprises receiving, by the server system, a query in natural language, processing the query using a natural language processing engine to generate graph query parameters, and executing the query against the graph database to retrieve results, wherein the results are provided to a user via an interface.

12 . The system of claim 11 , wherein the user-generated data is received via a user interface of the knowledge graph.

13 . The system of claim 12 , wherein the user-generated data includes a self-identification from a user as a user of the one or more architecture nodes.

14 . The system of claim 12 , wherein the user-generated data includes a comment regarding an evaluated architecture represented by the one or more architecture nodes.

15 . The system of claim 12 , wherein the user-generated data includes a quality score regarding an evaluated architecture represented by the one or more architecture nodes.

16 . The system of claim 11 , wherein instructions stored on the memory instruct the processor to:

receive, at a query engine, a natural language query;

process the natural language query with a natural language query processing engine;

generate, as a result of the processing the natural language query with the natural language processing engine, a plurality of graph properties;

query the knowledge graph using the plurality of graph properties as parameters; and

display the results of the querying through the interface.

17 . The system of claim 16 , wherein instructions stored on the memory instruct the processor to:

format, by the query engine, the results of the querying into a natural language format.

18 . The system of claim 17 , wherein the natural language query is associated with a confidence score.

19 . The system of claim 18 , wherein instructions stored on the memory instruct the processor to:

receive positive feedback from a submitter of the natural language query with respect to an accuracy of the results of the querying.

20 . A non-transitory computer readable storage medium, including instructions stored thereon for building, maintaining, and querying a unified asset graph, which when read and executed by one or more computers cause the one or more computers to perform steps comprising:

determining an intended state and a functional state of a plurality of evaluated architectures of an evaluating organization;