IP Library Granted Patent US 12,367,127
Granted Patent B2
US 12,367,127 · App. 18/302,138 · Granted Jul 22, 2025

Dynamic response generation based on an anomaly associated with a software application

Inventors: Nipun Mahajan (Lawrenceville, NJ); Pravin Kumar Sankari Bhagavathiappan (Kanyakumari District, IN); Amit Mishra (Chennai, IN); Yogesh Raghuvanshi (Princeton, NJ)
Assignee: Bank of America Corporation
G06F11/3612G06F11/3698
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 12,367,127
App. No.
18/302,138
Granted
Jul 22, 2025
Kind
B2
Abstract

A system determines content indicated on a website where a software application is accessible. The system receives a set of rules comprising a first rule that indicates a first generated response is to be published on one or more first platforms. The system generates a first text response according to the first rule and based on the determined content, an anomaly associated with a software application, and a countermeasure action that addresses or resolves the anomaly. The system determines whether the first generated text response corresponds to an expected response. In response to determining that the first generated text response corresponds to the expected response, the system publishes the first generated text response on the one or more first platforms.

Claims (62)

1. A system for generating a dynamic response based on an anomaly associated with a software application, comprising:

a memory configured to store:

a text message indicating an anomaly associated with a software application and a countermeasure action that addresses or resolves the anomaly; and

a training dataset that comprises an expected response labeled with the software application;

a processor operably coupled to the memory, and configured to:

determine content indicated on a website where the software application is accessible, wherein the content comprises text written on the website;

receive a set of rules comprising a first rule that indicates a first generated response is to be published on one or more first platforms, wherein the one or more first platforms comprises at least one of the website or a mobile application where the software application is accessed;

based at least in part upon the text message and the determined content, generate a first text response according to the first rule, wherein the first text response indicates that the anomaly associated with the software application is being addressed;

determine whether the first generated text response corresponds to the expected response; and

in response to determining that the first generated text response corresponds to the expected response, publish the first generated text response on the one or more first platforms.

2. The system of claim 1 , wherein the set of rules further comprises a second rule that indicates that a second generated response is to be published on a second platform.

3. The system of claim 2 , wherein the processor is further configured to:

based at least in part upon the text message and the determined content, generate a second response according to the second rule, wherein the second generated text response indicates that a service provided by the software application is currently interrupted; and

publish the second generated text response on the second platform.

4. The system of claim 2 , wherein the second rule further indicates that the second generated text response should not indicate the anomaly.

5. The system of claim 1 , wherein the processor is further configured to:

in response to determining that the first generated text response does not correspond to the expected response:

update weight and bias values of a neural network implemented by the processor; and

update the first text response based at least in part upon the updated weight and the updated bias values of the neural network.

6. The system of claim 1 , wherein:

before the first text response is generated, the processor is further configured to receive a legal text template that indicates information that can be included in the first generated response and information that cannot be included in the first generated response; and

the first generated response is generated further based at least in part upon the legal text template.

7. The system of claim 1 , wherein at least a portion of the text written on the website is used to generate the first generated response.

8. A method for generating a dynamic response based on an anomaly associated with a software application, comprising:

storing a text message indicating an anomaly associated with a software application and a countermeasure action that addresses or resolves the anomaly;

storing a training dataset that comprises an expected response labeled with the software application;

determining content indicated on a website where the software application is accessible, wherein the content comprises text written on the website;

receiving a set of rules comprising a first rule that indicates a first generated response is to be published on one or more first platforms, wherein the one or more first platforms comprises at least one of the website or a mobile application where the software application is accessed;

based at least in part upon the text message and the determined content, generating a first text response according to the first rule, wherein the first text response indicates that the anomaly associated with the software application is being addressed;

determining whether the first generated text response corresponds to the expected response; and

in response to determining that the first generated text response corresponds to the expected response, publishing the first generated text response on the one or more first platforms.

9. The method of claim 8 , wherein the set of rules further comprises a second rule that indicates that a second generated response is to be published on a second platform.

10. The method of claim 9 , further comprising:

based at least in part upon the text message and the determined content, generating a second response according to the second rule, wherein the second generated text response indicates that a service provided by the software application is currently interrupted; and

publishing the second generated text response on the second platform.

11. The method of claim 9 , wherein the second rule further indicates that the second generated text response should not indicate the anomaly.

12. The method of claim 8 , further comprising:

in response to determining that the first generated text response does not correspond to the expected response:

updating weight and bias values of a neural network implemented by a processor; and

updating the first text response based at least in part upon the updated weight and the updated bias values of the neural network.

13. The method of claim 8 , wherein:

before the first text response is generated, the method further comprises receiving a legal text template that indicates information that can be included in the first generated response and information that cannot be included in the first generated response; and

the first generated response is generated further based at least in part upon the legal text template.

14. The method of claim 8 , wherein at least a portion of the text written on the website is used to generate the first generated response.

15. A non-transitory computer-readable medium storing instructions that when executed by a processor, cause the processor to:

store a text message indicating an anomaly associated with a software application and a countermeasure action that addresses or resolves the anomaly;

store a training dataset that comprises an expected response labeled with the software application;

determine content indicated on a website where the software application is accessible, wherein the content comprises text written on the website;

receive a set of rules comprising a first rule that indicates a first generated response is to be published on one or more first platforms, wherein the one or more first platforms comprises at least one of the website or a mobile application where the software application is accessed;

based at least in part upon the text message and the determined content, generate a first text response according to the first rule, wherein the first text response indicates that the anomaly associated with the software application is being addressed;

determine whether the first generated text response corresponds to the expected response; and

in response to determining that the first generated text response corresponds to the expected response, publish the first generated text response on the one or more first platforms.

16. The non-transitory computer-readable medium of claim 15 , wherein the set of rules further comprises a second rule that indicates that a second generated response is to be published on a second platform.

17. The non-transitory computer-readable medium of claim 16 , wherein the instructions further cause the processor to:

based at least in part upon the text message and the determined content, generate a second response according to the second rule, wherein the second generated text response indicates that a service provided by the software application is currently interrupted; and

publish the second generated text response on the second platform.

18. The non-transitory computer-readable medium of claim 16 , wherein the second rule further indicates that the second generated text response should not indicate the anomaly.

19. The non-transitory computer-readable medium of claim 15 , wherein the instructions further cause the processor to:

in response to determining that the first generated text response does not correspond to the expected response:

update weight and bias values of a neural network implemented by the processor; and

update the first text response based at least in part upon the updated weight and the updated bias values of the neural network.

20. The non-transitory computer-readable medium of claim 15 , wherein determining the content indicated on the website associated with the software application is in response to parsing the website to extract the text.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 18, 2023
From: MAHAJAN, NIPUN; MISHRA, AMIT; SANKARI BHAGAVATHIAPPAN, PRAVIN KUMAR; RAGHUVANSHI, YOGESH
To: BANK OF AMERICA CORPORATION
Reel/Frame 063360/0159 →
Continuity (1)
Related Publication 20240354220A1 · Oct 24, 2024
References Cited (34)
US 7401145B2 · Kang et al. · 2008 [cited by applicant]
US 7773611B2 · Booth, III et al. · 2010 [cited by applicant]
US 7974714B2 · Hoffberg · 2011 [cited by applicant]
US 8296605B2 · John · 2012 [cited by examiner]
US 8468244B2 · Redlich et al. · 2013 [cited by applicant]
US 8527814B1 · Elwell · 2013 [cited by examiner]
US 8745213B2 · Dare · 2014 [cited by examiner]
US 8768731B2 · Moore · 2014 [cited by applicant]
US 9204796B2 · Tran · 2015 [cited by applicant]
US 9213850B2 · Barton · 2015 [cited by examiner]
US 9215244B2 · Ayyagari et al. · 2015 [cited by applicant]
US 9569426B1 · Bostick · 2017 [cited by examiner]
US 9769306B2 · Lang · 2017 [cited by examiner]
US 10117066B2 · Addepalli et al. · 2018 [cited by applicant]
US 10558516B2 · Leverich et al. · 2020 [cited by applicant]
US 10817586B2 · Wang · 2020 [cited by examiner]
US 10891558B2 · Ben Simhon et al. · 2021 [cited by applicant]
US 10911470B2 · Muddu et al. · 2021 [cited by applicant]
US 11113011B2 · Kondoh · 2021 [cited by examiner]
US 11221839B2 · Kulkarni · 2022 [cited by examiner]
US 11579958B2 · Gonzalez Macias · 2023 [cited by examiner]
US 11615424B2 · Birsan · 2023 [cited by examiner]
US 20170007148A1 · Kaditz et al. · 2017 [cited by applicant]
US 20170279835A1 · Di Pietro et al. · 2017 [cited by applicant]
US 20170339178A1 · Mahaffey et al. · 2017 [cited by applicant]
US 20190227536A1 · Cella et al. · 2019 [cited by applicant]
US 20200067969A1 · Abbaszadeh et al. · 2020 [cited by applicant]
US 20200228558A1 · Apostolopoulos · 2020 [cited by applicant]
US 20200342233A1 · Chang et al. · 2020 [cited by applicant]
US 20200357062A1 · Belanger et al. · 2020 [cited by applicant]
US 20200379454A1 · Trinh et al. · 2020 [cited by applicant]
US 20210110282A1 · McCann · 2021 [cited by examiner]
US 20230213973A1 · Xu · 2023 [cited by examiner]
Mahajan, Nipun, “Anomaly detection from network traffic,” U.S. Appl. No. 18/302,122 filed Apr. 18, 2023 (47 pages). [cited by applicant]