IP Library Granted Patent US 12,248,583
Granted Patent B2
US 12,248,583 · App. 17/888,037 · Granted Mar 11, 2025

Systems and methods for encrypting dialogue based data in a data storage system

Inventors: Dalydas Karanath (Kerala, IN); Syed Najumudeen (Telangana, IN); Radhika Vinaikrishnan Nair (Maharashtra, IN)
Assignee: BANK OF AMERICA CORPORATION
G06F21/60G06F16/686G06F21/6218G10L17/02
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 12,248,583
App. No.
17/888,037
Granted
Mar 11, 2025
Kind
B2
Abstract

Embodiments of the invention are directed to systems, methods, and computer program products that provide a unique platform for analyzing, classifying, extracting, and dialogue information from audio file recordings between a customer and an agent of an entity. In particular, the novel present invention provides a unique platform for analyzing, classifying, extracting, and processing information from call recordings using an image-based encryption method and cognitive neural engine in order to segment audio files according to speaker, and later analyze recording information to generate contextual inferences regarding user preferences and agent performance.

Claims (57)

1. A system for secure information storage analysis, the system comprising:

at least one memory device with computer-readable program code stored thereon;

at least one communication device;

at least one processing device operatively coupled to the at least one memory device and the at least one communication device, wherein executing the computer-readable code is configured to cause the at least one processing device to:

record an audio file of a call between one or more users;

generate a wave transform of the audio file by processing the audio file via a 16 bit quantifier to produce the wave transformation in image file form;

analyze the wave transform of the audio file to identify segments of the audio file which represent the voice of each of the one or more users;

store timestamps, an image key, and user data corresponding to each of the identified segments of the audio file; and

encrypt each of the identified segments of the audio file using a steganographic application of the image file, wherein the steganographic application of the image file further comprises using a steganographic chaos encryption function, wherein the steganographic chaos encryption permutates and diffuses positions of the pixels in the image file associated with the encrypted individual segments of the audio file.

2. The system of claim 1 , further configured to:

convert an encrypted audio file back to an original audio file; and

apply a cognitive processing engine to extract one or more contextual inferences from the original audio file.

3. The system of claim 1 , further configured to:

receive a request for decryption of the identified segments of the audio file;

respond to the request for decryption with a request for one or more authentication credentials;

receive the one or more authentication credentials;

determine if the one or more authentication credentials are valid; and

based on the authentication credentials provided, respond to the request for decryption with an automated decryption and delivery of a limited number of the identified segments of the audio file.

4. The system of claim 1 , wherein the image file is randomly or pseudo randomly chosen for each of the identified segments of the audio file.

5. The system of claim 1 , wherein each of the identified segments of the audio file is linked using hashing key and timestamp based a time sequence.

6. The system of claim 2 , wherein the one or more contextual inferences further comprise client preferences or conversational anomalies during the course of a customer service interaction.

7. A computer program product for secure information storage analysis with at least one non-transitory computer-readable medium having computer-readable program code portions embodied therein, the computer-readable program code portions comprising:

an executable portion configured to record an audio file of a call between one or more users;

an executable portion configured to generate a wave transform of the audio file by processing the audio file via a 16 bit quantifier to produce the wave transformation in image file form;

an executable portion configured to analyze the wave transform of the audio file to identify segments of the audio file which represent the voice of each of the one or more users;

an executable portion configured to store timestamps, an image key, and user data corresponding to each of the identified segments of the audio file; and

an executable portion configured to encrypt each of the identified segments of the audio file using a steganographic application of the image file, wherein the steganographic application of the image file further comprises using a steganographic chaos encryption function, wherein the steganographic chaos encryption permutates and diffuses positions of the pixels in the image file associated with the encrypted individual segments of the audio file.

8. The computer program product of claim 7 , further comprising:

an executable portion configured to convert an encrypted audio file back to an original audio file; and

an executable portion configured to apply a cognitive processing engine to extract one or more contextual inferences from the original audio file.

9. The computer program product of claim 7 , further comprising:

an executable portion configured to receive a request for decryption of the identified segments of the audio file;

an executable portion configured to respond to the request for decryption with a request for one or more authentication credentials;

an executable portion configured to receive the one or more authentication credentials;

an executable portion configured to determine if the one or more authentication credentials are valid; and

an executable portion configured to, based on the authentication credentials provided, respond to the request for decryption with an automated decryption and delivery of a limited number of the identified segments of the audio file.

10. The computer program product of claim 7 , wherein the image file is randomly or pseudo randomly chosen for each of the identified segments of the audio file.

11. The computer program product of claim 7 , wherein each of the identified segments of the audio file is linked using hashing key and timestamp based a time sequence.

12. The computer program product of claim 8 , wherein the one or more contextual inferences further comprise client preferences or conversational anomalies during the course of a customer service interaction.

13. A computer implemented method for secure information storage analysis, said computer implemented method comprising:

providing a computing system comprising a computer processing device and a non-transitory computer readable medium, where the computer readable medium comprises configured computer program instruction code, such that when said instruction code is operated by said computer processing device, said computer processing device performs the following operations:

record an audio file of a call between one or more users;

generate a wave transform of the audio file by processing the audio file via a 16 bit quantifier to produce the wave transformation in image file form;

analyze the wave transform of the audio file to identify segments of the audio file which represent the voice of each of the one or more users;

store timestamps, an image key, and user data corresponding to each of the identified segments of the audio file; and

encrypt each of the identified segments of the audio file using a steganographic application of the image file, wherein the steganographic application of the image file further comprises using a steganographic chaos encryption function, wherein the steganographic chaos encryption permutates and diffuses positions of the pixels in the image file associated with the encrypted individual segments of the audio file.

14. The computer-implemented method of claim 13 , further configured to:

convert an encrypted audio file back to an original audio file; and

apply a cognitive processing engine to extract one or more contextual inferences from the original audio file.

15. The computer-implemented method of claim 13 , further configured to:

receive a request for decryption of the identified segments of the audio file;

respond to the request for decryption with a request for one or more authentication credentials;

receive the one or more authentication credentials;

determine if the one or more authentication credentials are valid; and

based on the authentication credentials provided, response to the request for decryption with an automated decryption and delivery of a limited number of the identified segments of the audio file.

16. The computer-implemented method of claim 13 , wherein the image file is randomly or pseudo randomly chosen for each of the identified segments of the audio file.

17. The computer-implemented method of claim 13 , wherein each of the identified segments of the audio file is linked using hashing key and timestamp based a time sequence.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 15, 2022
From: KARANATH, DALYDAS; NAJUMUDEEN, SYED; NAIR, RADHIKA VINAIKRISHNAN
To: BANK OF AMERICA CORPORATION
Reel/Frame 060810/0128 →
Continuity (1)
Related Publication 20240054235A1 · Feb 15, 2024
References Cited (35)
US 6064738A · Fridrich · 2000 [cited by examiner]
US 7330563B2 · Rhoads · 2008 [cited by applicant]
US 7466840B2 · Rhoads · 2008 [cited by applicant]
US 7486799B2 · Rhoads · 2009 [cited by applicant]
US 7676059B2 · Rhoads · 2010 [cited by applicant]
US 7769174B2 · Cho et al. · 2010 [cited by applicant]
US 7805377B2 · Felsher · 2010 [cited by applicant]
US 7970167B2 · Rhoads · 2011 [cited by applicant]
US 7986773B2 · Kalahasti et al. · 2011 [cited by applicant]
US 7987245B2 · Rhoads · 2011 [cited by applicant]
US 8023695B2 · Rhoads · 2011 [cited by applicant]
US 8078697B2 · Rhoads · 2011 [cited by applicant]
US 8204222B2 · Rhoads · 2012 [cited by applicant]
US 8265278B2 · Moskowitz et al. · 2012 [cited by applicant]
US 8316237B1 · Felsher et al. · 2012 [cited by applicant]
US 8401155B1 · Barnes et al. · 2013 [cited by applicant]
US 8411898B2 · Rhoads · 2013 [cited by applicant]
US 8831204B1 · Pycko et al. · 2014 [cited by applicant]
US 8972736B2 · Peirce et al. · 2015 [cited by applicant]
US 9596344B2 · Lum et al. · 2017 [cited by applicant]
US 9787835B1 · Pycko et al. · 2017 [cited by applicant]
US 11295029B1 · Greenblatt · 2022 [cited by examiner]
US 11893464B1 · Everest · 2024 [cited by examiner]
US 20030115451A1 · Walker et al. · 2003 [cited by applicant]
US 20040111399A1 · Rice · 2004 [cited by examiner]
US 20050114234A1 · Thomas · 2005 [cited by examiner]
US 20090185673A1 · Erhart et al. · 2009 [cited by applicant]
US 20110222688A1 · Graham et al. · 2011 [cited by applicant]
US 20150058017A1 · Singh · 2015 [cited by examiner]
US 20150099469A1 · Goldstein · 2015 [cited by examiner]
US 20170221488A1 · Xiong · 2017 [cited by examiner]
US 20170310820A1 · Kao · 2017 [cited by examiner]
US 20230274377A1 · Kulshrestha · 2023 [cited by examiner]
US 20230386642A1 · Foufa · 2023 [cited by examiner]
US 20240135949A1 · Eskimez · 2024 [cited by examiner]