IP Library › Granted Patent US 12,737,557
Granted Patent B2
US 12,737,557 · App. 18/491,090 · Granted Sep 15, 2026

GUI for layered transformative AI data article compression

Inventors: Ali Rezajoo (Charlotte, NC); James Harrison Creager (Raleigh, NC)
Assignee: TRUIST BANK
G06F40/40G06F40/166G06N3/044G06N3/0464G06F3/04842
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 12,737,557
App. No.
18/491,090
Filed
Oct 20, 2023
Granted
Sep 15, 2026
Kind
B2
Art Unit
2172
USPC
715/254
Abstract

A system for generating a graphical user interface for prompting layered transformative data article compression by artificial intelligence is configured to generate a second data article by, at least in part, compressing a first data article using a first AI algorithm trained by a machine-learning technique, and send the second data article with instructions to display at least a portion of the second data article at the user device. Compressing the first data article using the AI algorithm includes: generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration; and generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration.

Claims (58)

1 . A system for generating a graphical user interface for prompting layered transformative data article compression at least in part by artificial intelligence (AI), the system comprising:

a computing system of a first entity including at least one processor configured to execute computer-readable instructions, at least one of a memory device and a non-transitory storage device, and a communication interface for operatively connecting the at least one processor to a user device via a communication network, the at least one of a memory device and a non-transitory storage device storing a user profile associated with the user device;

wherein, upon execution of the computer-readable instructions, the at least one processor is configured to:

access a first data article;

transmit the first data article to the user device via the communication network with instructions to generate a graphical user interface that displays at least a portion of the first data article and an operable compression request selector at the user device;

receive from the user device via the communication network a selector signal indicative of user action on the operable compression request selector;

generate a second data article by, at least in part, compressing the first data article using an AI algorithm trained by a machine-learning technique; and

send the second data article via the communication network with instructions to display at least a portion of the second data article at the user device,

wherein compressing the first data article using the AI algorithm comprises:

generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration;

accessing the user profile; and

generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration according to at least one setting stored in the user profile.

2 . The system of claim 1 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises translating content of the first data article from a first language to a second language of the second data article.

3 . The system of claim 2 , wherein the second language comprises a natural language format and the first language comprises at least one of a legal format and a technical format.

4 . The system of claim 1 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of: shortening content of the first data article; summarizing content of the first data article; and simplifying content of the first data article.

5 . The system of claim 1 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of:

shortening content of the first data article while maintaining semantic meaning;

decomposing at least one sentence longer than a threshold number of words into multiple sentences each having a number of words less than the threshold number of words; and

replacing at least one word having a threshold number of letters with one or more replacement words extracted from a thesaurus, the one or more replacement words each having less than the threshold number of letters.

6 . The system of claim 1 , wherein generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration comprises accessing the user profile and at least one of: checking a user preference; deducing a user preference; and inferring a user preference.

7 . The system of claim 1 , wherein content of the first data article comprises at least one of: information about an offering by the first entity; and, terms and conditions for an offering by the first entity.

8 . A system for generating a graphical user interface for prompting layered transformative data article compression at least in part by artificial intelligence (AI), the system comprising:

a computing system of a first entity including at least one processor configured to execute computer-readable instructions, at least one of a memory device and a non-transitory storage device, and a communication interface for operatively connecting the at least one processor to a user device via a communication network, the at least one of a memory device and a non-transitory storage device storing a user profile associated with the user device;

wherein, upon execution of the computer-readable instructions, the at least one processor is configured to:

access a first data article;

generate a second data article by, at least in part, compressing the first data article using an AI algorithm trained by a machine-learning technique; and

send the second data article to the user device via the communication network with instructions to generate a graphical user interface that displays at least a portion of the second data article at the user device,

wherein compressing the first data article using the AI algorithm comprises:

generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration;

accessing the user profile; and

generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration according to at least one setting stored in the user profile.

9 . The system of claim 8 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises translating content of the first data article from a first language to a second language of the second data article.

10 . The system of claim 9 , wherein the second language comprises a natural language format and the first language comprises at least one of a legal format and a technical format.

11 . The system of claim 8 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of: shortening content of the first data article; summarizing content of the first data article; and simplifying content of the first data article.

12 . The system of claim 8 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of:

shortening content of the first data article while maintaining semantic meaning;

decomposing at least one sentence longer than a threshold number of words into multiple sentences each having a number of words less than the threshold number of words; and

replacing at least one word having a threshold number of letters with one or more replacement words extracted from a thesaurus, the replacement words each having less than the threshold number of letters.

13 . The system of claim 8 , wherein generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration comprises accessing the user profile and at least one of: checking a user preference; deducing a user preference; and inferring a user preference.

14 . The system of claim 8 , wherein content of the first data article comprises at least one of: information about an offering by the first entity; and, terms and conditions for an offering by the first entity.

15 . A method for a computing system to generate a graphical user interface for prompting transformative data article compression at least in part by artificial intelligence (AI), the computing system being of a first entity and including at least one processor configured to execute computer-readable instructions, at least one of a memory device and a non-transitory storage device, and a communication interface for operatively connecting the at least one processor to a user device via a communication network, the at least one of a memory device and a non-transitory storage device storing a user profile associated with the user device, the method comprising, upon executing the computer-readable instructions, the at least one processor operating the computing system to:

access a first data article;

transmit the first data article to the user device via the communication network with instructions to generate a graphical user interface that displays at least a portion of the first data article and an operable compression request selector at the user device;

receive from the user device via the communication network a selector signal indicative of user action on the operable compression request selector;

generate a second data article by, at least in part, compressing the first data article using an AI algorithm trained by a machine-learning technique; and

send the second data article via the communication network with instructions to display at least a portion of the second data article at the user device,

wherein compressing the first data article using the AI algorithm comprises:

generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration;

accessing the user profile; and

generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration according to at least one setting stored in the user profile.

16 . The method of claim 15 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises translating content of the first data article from a first language to a second language of the second data article.

17 . The method of claim 16 , wherein the second language comprises a natural language format and the first language comprises at least one of a legal format and a technical format.

18 . The method of claim 15 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of: shortening content of the first data article; summarizing content of the first data article; and simplifying content of the first data article.

19 . The method of claim 15 , wherein generating an interim data article by the AI algorithm translating the first data article in at least one user-profile agnostic iteration comprises at least one of:

shortening content of the first data article while maintaining semantic meaning;

decomposing at least one sentence longer than a threshold number of words into multiple sentences each having a number of words less than the threshold number of words; and

replacing at least one word having a threshold number of letters with one or more replacement words extracted from a thesaurus, the replacement words each having less than the threshold number of letters.

20 . The method of claim 15 , wherein generating the second data article by the AI algorithm translating the interim data article in at least one user-profile dependent iteration comprises accessing the user profile and at least one of: checking a user preference; deducing a user preference; and inferring a user preference.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 20, 2023
From: REZAJOO, ALI; CREAGER, JAMES HARRISON
To: TRUIST BANK
Reel/Frame 065294/0062 →
Continuity (1)
Related Publication 20250131205A1 · Apr 24, 2025
References Cited (25)
US 10453454B2 · Homma · 2019 [cited by examiner]
US 10585991B2 · Miller · 2020 [cited by examiner]
US 11172272B2 · Wang · 2021 [cited by examiner]
US 11500917B2 · Wu · 2022 [cited by examiner]
US 11580350B2 · Wu · 2023 [cited by examiner]
US 12393875B2 · Strope · 2025 [cited by examiner]
US 12518447B2 · Dibia · 2026 [cited by applicant]
US 20170083200A1 · Bartley · 2017 [cited by examiner]
US 20180373705A1 · Kwon · 2018 [cited by examiner]
US 20190108282A1 · Zeng · 2019 [cited by examiner]
US 20190327330A1 · Natarajan · 2019 [cited by applicant]
US 20190370336A1 · Prakash · 2019 [cited by examiner]
US 20200143384A1 · Koontz · 2020 [cited by applicant]
US 20210326536A1 · Hutchins · 2021 [cited by examiner]
US 20240089903A1 · Monteuuis · 2024 [cited by examiner]
US 20240185490A1 · Dibia · 2024 [cited by examiner]
US 20240320684A1 · Ramalingam · 2024 [cited by applicant]
US 20250131204A1 · Rezajoo · 2025 [cited by applicant]
US 20250131205A1 · Rezajoo · 2025 [cited by applicant]
US 20250181982A1 · Everest · 2025 [cited by applicant]
US 20250258994A1 · Plotkin · 2025 [cited by examiner]
US 20250265413A1 · Hernandez · 2025 [cited by examiner]
US 20250298973A1 · Haleva · 2025 [cited by examiner]
US 20250315630A1 · Shernan · 2025 [cited by examiner]
US 20250329256A1 · Balasubramanian · 2025 [cited by examiner]