IP Library › Granted Patent US 12,731,464
Granted Patent B2
US 12,731,464 · App. 19/232,962 · Granted Sep 8, 2026

Generative artificial intelligence-based automated teller machine process generation

Inventors: Paul Mattison (Charlotte, NC); Matthew Williams (Plano, TX); Jennifer Raley (Mount Holly, NC)
Assignee: Bank of America Corporation
G07F19/201
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 12,731,464
App. No.
19/232,962
Granted
Sep 8, 2026
Kind
B2
Abstract

Arrangements for using generative artificial intelligence models for ATM process generation are provided. In some examples, a computing platform may receive, from at least one image or measurement capture device, dimension data associated with an ATM. The ATM may have a plurality of components arranged on a face of the ATM. The dimension data may be input to a generative artificial intelligence model and the model may be executed to output, based on the dimension data, a position or location of each ATM component relative to a reference point on the ATM. In some examples, the model may further output at least one audio script describing the location of each component. The model may output one or more translations of the at least one audio script. The computing platform may transmit or send the at least one audio script to the ATM for presentation during user interaction with the ATM.

Claims (46)

1 . A computing platform, comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

a memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

train, using historical data related to at least automated teller machine (ATM) dimensions and audio scripts, a generative artificial intelligence model to identify correlations in subsequent data and output content based on the identified correlations, wherein the generative artificial intelligence model includes a variational encoder;

receive, from at least one image or measurement capture device, dimension data associated with an automated teller machine (ATM) having a plurality of ATM components;

input, to the generative artificial intelligence model, the dimension data associated with the ATM;

execute the generated artificial intelligence model to output, based on the input dimension data associated with the ATM, a location of each ATM component of the plurality of ATM components relative to a reference point on the ATM and at least one audio script describing the location of each component of the plurality of ATM components; and

transmit, to the ATM, the at least one audio script for presentation to a user during a user interaction with the ATM.

2 . The computing platform of claim 1 , wherein training the generative artificial intelligence model further includes:

training the generative artificial intelligence model further based on regulatory requirement data associated with ATM structure.

3 . The computing platform of claim 2 , wherein executing the generated artificial intelligence model further includes outputting an indication of compliance of the ATM and the location of each component of the plurality of ATM components with regulatory requirements in the regulatory requirement data.

4 . The computing platform of claim 1 , further including instructions that, when executed, cause the computing platform to:

further output, by the generative artificial intelligence model, translations of the at least one audio script into a plurality of languages.

5 . The computing platform of claim 1 , wherein transmitting, to the ATM, the at least one audio script for presentation to the user during a user interaction with the ATM causes the ATM to provide audio data including the at least one audio script in response to user insertion of a headphone connection into a headphone jack of the ATM.

6 . The computing platform of claim 1 , wherein the plurality of ATM components includes at least a card reader, a cash dispensing slot, a deposit receiving slot and a headphone jack.

7 . The computing platform of claim 6 , wherein the reference point is a number five (5) key on a keypad of the ATM.

8 . The computing platform of claim 1 , further including instructions that, when executed cause the computing platform to:

prior to transmitting, to the ATM, the at least one audio script for presentation to the user during the user interaction with the ATM, execute at least one test to confirm accuracy of the at least one audio script.

9 . A method, comprising:

training, by a computing platform, the computing platform having at least one processor and memory, and using historical data related to at least automated teller machine (ATM) dimensions and audio scripts, a generative artificial intelligence model to identify correlations in subsequent data and output content based on the identified correlations, wherein the generative artificial intelligence model includes a variational encoder;

receiving, by the at least one processor and memory, and from at least one image or measurement capture device, dimension data associated with an automated teller machine (ATM) having a plurality of ATM components;

inputting, by the at least one processor and to the generative artificial intelligence model, the dimension data associated with the ATM;

executing, by the at least one processor, the generated artificial intelligence model to output, based on the input dimension data associated with the ATM, a location of each ATM component of the plurality of ATM components relative to a reference point on the ATM and at least one audio script describing the location of each component of the plurality of ATM components; and

transmitting, by the at least one processor and to the ATM, the at least one audio script for presentation to a user during a user interaction with the ATM.

10 . The method of claim 9 , wherein training the generative artificial intelligence model further includes:

training, by the at least one processor, the generative artificial intelligence model further based on regulatory requirement data associated with ATM structure.

11 . The method of claim 10 , wherein executing the generated artificial intelligence model further includes outputting an indication of compliance of the ATM and the location of each component of the plurality of ATM components with regulatory requirements in the regulatory requirement data.

12 . The method of claim 9 , further including:

further outputting, by the generative artificial intelligence model, translations of the at least one audio script into a plurality of languages.

13 . The method of claim 9 , wherein transmitting, to the ATM, the at least one audio script for presentation to the user during a user interaction with the ATM causes the ATM to provide audio data including the at least one audio script in response to user insertion of a headphone connection into a headphone jack of the ATM.

14 . The method of claim 9 , wherein the plurality of ATM components include at least a card reader, a cash dispensing slot, a deposit receiving slot and a headphone jack.

15 . The method of claim 14 , wherein the reference point is a number five (5) key on a keypad of the ATM.

16 . The method of claim 9 , further:

prior to transmitting, to the ATM, the at least one audio script for presentation to the user during the user interaction with the ATM, executing, by the at least one processor, at least one test to confirm accuracy of the at least one audio script.

17 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:

train, using historical data related to at least automated teller machine (ATM) dimensions and audio scripts, a generative artificial intelligence model to identify correlations in subsequent data and output content based on the identified correlations, wherein the generative artificial intelligence model includes a variational encoder;

receive, from at least one image or measurement capture device, dimension data associated with an automated teller machine (ATM) having a plurality of ATM components;

input, to the generative artificial intelligence model, the dimension data associated with the ATM;

execute the generated artificial intelligence model to output, based on the input dimension data associated with the ATM, a location of each ATM component of the plurality of ATM components relative to a reference point on the ATM and at least one audio script describing the location of each component of the plurality of ATM components; and

transmit, to the ATM, the at least one audio script for presentation to a user during a user interaction with the ATM.

18 . The one or more non-transitory computer-readable media of claim 17 , wherein training the generative artificial intelligence model further includes instructions that, when executed, cause the computing platform to:

train the generative artificial intelligence model further based on regulatory requirement data associated with ATM structure.

19 . The one or more non-transitory computer-readable media of claim 18 , wherein executing the generated artificial intelligence model further includes outputting an indication of compliance of the ATM and the location of each component of the plurality of ATM components with regulatory requirements in the regulatory requirement data.

20 . The one or more non-transitory computer-readable media of claim 17 , further including instructions that, when executed, cause the computing platform to:

further output, by the generative artificial intelligence model, translations of the at least one audio script into a plurality of languages.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 10, 2025
From: MATTISON, PAUL; WILLIAMS, MATTHEW; RALEY, JENNIFER
To: BANK OF AMERICA CORPORATION
Reel/Frame 071369/0434 →
Continuity (2)
Continuation 18654126 · May 3, 2024
Related Publication 20250342754A1 · Nov 6, 2025
References Cited (25)
US 10380788B2 · Martinez · 2019 [cited by applicant]
US 10789755B2 · Amer et al. · 2020 [cited by applicant]
US 10949652B1 · Cruz et al. · 2021 [cited by applicant]
US 11042800B2 · Mars et al. · 2021 [cited by applicant]
US 11164581B2 · Chae et al. · 2021 [cited by applicant]
US 11429712B2 · Ortiz et al. · 2022 [cited by applicant]
US 11429976B1 · Jain et al. · 2022 [cited by applicant]
US 11521273B2 · Jakka et al. · 2022 [cited by applicant]
US 12347283B1 · Mattison · 2025 [cited by examiner]
US 20190033849A1 · Cella et al. · 2019 [cited by applicant]
US 20190095775A1 · Lembersky et al. · 2019 [cited by applicant]
US 20190295093A1 · Buckley et al. · 2019 [cited by applicant]
US 20230129964A1 · Rodriguez Bravo et al. · 2023 [cited by applicant]
US 20230237567A1 · Kar et al. · 2023 [cited by applicant]
US 20250054375A1 · Chesley · 2025 [cited by examiner]
US 20250165864A1 · Ghosh et al. · 2025 [cited by applicant]
US 20250173692A1 · Gupta · 2025 [cited by applicant]
US 20250299164A1 · Mueller et al. · 2025 [cited by applicant]
US 20250335889A1 · Baker et al. · 2025 [cited by applicant]
US 20250335891A1 · Baker et al. · 2025 [cited by applicant]
Nov. 22, 2024—(US) Non-Final Office Action—U.S. Appl. No. 18/654,126. [cited by applicant]
Dec. 19, 2024—(US) Non-Final Office Action—U.S. Appl. No. 18/654,188. [cited by applicant]
Mar. 13, 2025—(US) Notice of Allowance—U.S. Appl. No. 18/654,126. [cited by applicant]
Apr. 10, 2025—(US) Notice of Allowance—U.S. Appl. No. 18/654,188. [cited by applicant]
Feb. 17, 2026—(US) Notice of Allowance—U.S. Appl. No. 18/654,154. [cited by applicant]