Granted Patent B2

US 12,254,116 · App. 18/620,470 · Granted Mar 18, 2025

Inventors: Pratap Dande (Saint Johns, FL); Akhila Mylaram (Frisco, TX); Gilberto R. Dos Santos (Jacksonville, FL); JayaBalaji Murugan (Tamil Nadu, IN)

Assignee: Bank of America Corporation

G06F21/6254G06F16/31

Abstract

Claims (97)

1. A system, comprising:

a memory configured to store:

a plurality of task logs comprising text that is confidential information; and

a training dataset comprising a set of keywords associated with the confidential information;

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

access the plurality of task logs;

for a first task log from among the plurality of task logs:

select a first portion of the first task log;

for a first word in the first portion:

compare the first word with each of the set of keywords, wherein comparing the first word with each of the set of keywords comprises:

 extracting a first set of features from the first word, wherein the first set of features indicates a first identity of the first word, wherein the first set of features is represented by a first vector of numerical values;

 extracting a second set of features from a second word of the set of keywords, wherein the second set of features indicates a second identity of the second word, wherein the second set of features is represented by a second vector of numerical values; and

 comparing the first vector with the second vector;

determine that the first word is among the set of keywords, wherein determining that the first word is among the set of keywords comprises:

 determining a percentage of numerical values in the first vector that correspond to counterpart numerical values in the second vector;

 comparing the determined percentage of numerical values in the first vector that correspond to the counterpart numerical values in the second vector to a threshold percentage; and

 determining that the determined percentage of numerical values exceeds the threshold percentage;

determine a hierarchical relationship between the first word and neighboring words in the first portion, wherein the hierarchical relationship between the first word and the neighboring words indicates whether or not the first word is associated with each of the neighboring words;

determine that the hierarchical relationship between the first word and the neighboring words indicates that the first word is associated with at least a third word in the first portion;

generate a template pattern comprising the first word and the third word, wherein the template pattern indicates that the first word and the third word are among the confidential information; and

obfuscate the first word and the third word.

2. The system of claim 1 , wherein obfuscating the first word and the third word comprises encrypting the first word and the third word using an encryption technique.

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

use the template pattern to identify other instances of the template pattern in the plurality of task logs; and

obfuscate the identified other instances of the template pattern; and

communicate the plurality of task logs with the obfuscated other instances of the template pattern.

4. The system of claim 1 , wherein:

each of the plurality of task logs has a different data format compared to other task logs; and

the different data format comprises structured data format, semi-structured data format, and unstructured data format.

5. The system of claim 1 , wherein each of the plurality of task logs is compressed with a different compression technique compared to other task logs.

6. The system of claim 1 , wherein the third word is included in the template pattern even if the third word is not among the set of keywords.

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

identify a fourth word in the first portion, wherein the fourth word is a name of a user who is authorized to access the first word and the third word;

after obfuscating the first word and the third word, communicate the obfuscated first word and the obfuscated third word to a computing device associated with the user;

receive, from the computing device, a request to decrypt the obfuscated first word and the obfuscated third word;

decrypt the obfuscated first word and the obfuscated third word; and

communicate the decrypted first word and the decrypted third word to the computing device.

8. A method, comprising:

accessing a plurality of task logs comprising text that is confidential information;

for a first task log from among the plurality of task logs:

selecting a first portion of the first task log;

for a first word in the first portion:

comparing the first word with each of a set of keywords, wherein the set of keywords included in a training dataset and associated with the confidential information, wherein comparing the first word with each of the set of keywords comprises:

extracting a first set of features from the first word, wherein the first set of features indicates a first identity of the first word, wherein the first set of features is represented by a first vector of numerical values;

extracting a second set of features from a second word of the set of keywords, wherein the second set of features indicates a second identity of the second word, wherein the second set of features is represented by a second vector of numerical values; and

comparing the first vector with the second vector;

determining that the first word is among the set of keywords, wherein determining that the first word is among the set of keywords comprises:

determining a percentage of numerical values in the first vector that correspond to counterpart numerical values in the second vector;

comparing the determined percentage of numerical values in the first vector that correspond to the counterpart numerical values in the second vector to a threshold percentage; and

determining that the determined percentage of numerical values exceeds the threshold percentage;

determining a hierarchical relationship between the first word and neighboring words in the first portion, wherein the hierarchical relationship between the first word and the neighboring words indicates whether or not the first word is associated with each of the neighboring words;

determining that the hierarchical relationship between the first word and the neighboring words indicates that the first word is associated with at least a third word in the first portion;

generating a template pattern comprising the first word and the third word, wherein the template pattern indicates that the first word and the third word are among the confidential information; and

obfuscating the first word and the third word.

9. The method of claim 8 , wherein obfuscating the first word and the third word comprises encrypting the first word and the third word using an encryption technique.

10. The method of claim 8 , further comprising:

using the template pattern to identify other instances of the template pattern in the plurality of task logs; and

obfuscating the identified other instances of the template pattern; and

communicating the plurality of task logs with the obfuscated other instances of the template pattern.

11. The method of claim 8 , wherein:

each of the plurality of task logs has a different data format compared to other task logs; and

the different data format comprises structured data format, semi-structured data format, and unstructured data format.

12. The method of claim 8 , wherein each of the plurality of task logs is compressed with a different compression technique compared to other task logs.

13. The method of claim 8 , wherein the third word is included in the template pattern even if the third word is not among the set of keywords.

14. The method of claim 8 , further comprising:

identifying a fourth word in the first portion, wherein the fourth word is a name of a user who is authorized to access the first word and the third word;

after obfuscating the first word and the third word, communicating the obfuscated first word and the obfuscated third word to a computing device associated with the user;

receiving, from the computing device, a request to decrypt the obfuscated first word and the obfuscated third word;

decrypting the obfuscated first word and the obfuscated third word; and

communicating the decrypted first word and the decrypted third word to the computing device.

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

access a plurality of task logs comprising text that is confidential information;

for a first task log from among the plurality of task logs:

select a first portion of the first task log;

for a first word in the first portion:

compare the first word with each of a set of keywords, wherein the set of keywords included in a training dataset and associated with the confidential information, wherein comparing the first word with each of the set of keywords comprises:

extracting a first set of features from the first word, wherein the first set of features indicates a first identity of the first word, wherein the first set of features is represented by a first vector of numerical values;

extracting a second set of features from a second word of the set of keywords, wherein the second set of features indicates a second identity of the second word, wherein the second set of features is represented by a second vector of numerical values; and

comparing the first vector with the second vector;

determine that the first word is among the set of keywords, wherein determining that the first word is among the set of keywords comprises:

determining a percentage of numerical values in the first vector that correspond to counterpart numerical values in the second vector;

comparing the determined percentage of numerical values in the first vector that correspond to the counterpart numerical values in the second vector to a threshold percentage; and

determining that the determined percentage of numerical values exceeds the threshold percentage;

determine a hierarchical relationship between the first word and neighboring words in the first portion, wherein the hierarchical relationship between the first word and the neighboring words indicates whether or not the first word is associated with each of the neighboring words;

determine that the hierarchical relationship between the first word and the neighboring words indicates that the first word is associated with at least a third word in the first portion;

generate a template pattern comprising the first word and the third word, wherein the template pattern indicates that the first word and the third word are among the confidential information; and

obfuscate the first word and the third word.

16. The non-transitory computer readable medium of claim 15 , wherein obfuscating the first word and the third word comprises encrypting the first word and the third word using an encryption technique.

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

use the template pattern to identify other instances of the template pattern in the plurality of task logs; and

obfuscate the identified other instances of the template pattern; and

communicate the plurality of task logs with the obfuscated other instances of the template pattern.

18. The non-transitory computer readable medium of claim 15 , wherein:

each of the plurality of task logs has a different data format compared to other task logs; and

the different data format comprises structured data format, semi-structured data format, and unstructured data format.

19. The non-transitory computer readable medium of claim 15 , wherein each of the plurality of task logs is compressed with a different compression technique compared to other task logs.

20. The non-transitory computer readable medium of claim 15 , wherein the third word is included in the template pattern even if the third word is not among the set of keywords.

Assignments (1)

Continuity (2)

References Cited (63)