System, method, and computer-accessible medium to verify data compliance by iterative learning

Patent metadata

Field	Value
Publication number	US-12045265-B2
Application number	US-202318127821-A
Country	US
Kind code	B2
Filing date	Mar 29, 2023
Priority date	Nov 1, 2019
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

An exemplary system, method, and computer-accessible medium can include, for example, establishing a unique rule-identifier in one-to-one correspondence with at least one set of unknown time-variable rules against which data is to be made compliant, obtaining at least one set of data marked compliant against the one or more set of rules, obtaining meta-data from the compliant data, obtaining at least one set of data marked non-compliant against the set of unknown time-variable rules, extracting meta-data from the non-compliant data, joining the set of compliant and non-compliant metadata to generate a set of estimated rules corresponding to the rule-identifier based at least one of (i) the meta-data of the joined set and (ii) machine learning algorithms.

First claim

What is claimed is:

1. A non-transitory computer-accessible medium having stored thereon computer-executable instructions wherein, when a computer hardware arrangement executes the instructions, the computer hardware arrangement is configured to perform procedures comprising:
obtaining meta-data from a compliant dataset, including a first date at which the compliant dataset became compliant against a first set of rules;
extracting meta-data from a non-compliant dataset;
joining the meta-data from the compliant dataset and the meta-data from the non-compliant dataset to create a joined dataset;
obtaining an unknown compliance dataset; and
marking the unknown compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on a set of estimated rules.

2. The non-transitory computer-accessible medium of claim 1 , further comprising generating the set of estimated rules based on the first date and the joined meta-data.

3. The non-transitory computer-accessible medium of claim 2 , wherein the set of estimated rule is generated by a machine learning algorithm.

4. The non-transitory computer-accessible medium of claim 2 , further comprising generating weights for each rule of the estimated set of rules.

5. The non-transitory computer-accessible medium of claim 4 , further comprising using a computer-based statistical method to classify an unknown set of data as compliant or non-compliant based on at least one of (i) statistical information from the unknown set of data and (ii) the generated weights of each rule of the estimated set of rules.

6. The non-transitory computer-accessible medium of claim 1 , further comprising appending additional data to the compliant dataset and re-verifying the appended dataset.

7. The non-transitory computer-accessible medium of claim 1 , further comprising iterating the process of verifying data compliance when a change in at least one of set of unknown time-variable rules is identified.

8. The non-transitory computer-accessible medium of claim 1 , further comprising generating a list of rules against which a set of data is compliant.

9. The non-transitory computer-accessible medium of claim 1 , further comprising classifying the joined meta-data dataset as compliant or non-compliant with respect to multiple sets of unknown time-variable rules.

10. A method, comprising:
obtaining meta-data from a compliant dataset, including a first date at which the compliant dataset became compliant against a first set of rules;
extracting meta-data from a non-compliant dataset;
joining the meta-data from the compliant dataset and the meta-data from the non-compliant dataset to create a joined dataset;
obtaining an unknown compliance dataset; and
marking the unknown compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on a set of estimated rules.

11. The method of claim 10 , further comprising generating the set of estimated rules based on the first date and the joined meta-data.

12. The method of claim 11 , wherein the set of estimated rule is generated by a machine learning algorithm.

13. The method of claim 11 , further comprising generating weights for each rule of the estimated set of rules.

14. The method of claim 13 , further comprising using a computer-based statistical method to classify an unknown set of data as compliant or non-compliant based on at least one of (i) statistical information from the unknown set of data and (ii) the generated weights of each rule of the estimated set of rules.

15. The method of claim 10 , further comprising appending additional data to the compliant dataset and re-verifying the appended dataset.

16. The method of claim 10 , further comprising iterating the process of verifying data compliance when a change in at least one of set of unknown time-variable rules is identified.

17. The method of claim 10 , further comprising generating a list of rules against which a set of data is compliant.

18. The method of claim 10 , further comprising classifying the joined meta-data dataset as compliant or non-compliant with respect to multiple sets of unknown time-variable rules.

19. A system, comprising:
A computer hardware arrangement consisting of at least a processor and memory, configured to:
obtain meta-data from a compliant dataset, including a first date at which the compliant dataset became compliant against a first set of rules;
extract meta-data from a non-compliant dataset;
join the meta-data from the compliant dataset and the meta-data from the non-compliant dataset to create a joined dataset;
obtain an unknown compliance dataset; and
mark the unknown compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on a set of estimated rules.

20. The system of claim 19 , further comprising generating the set of estimated rules based on the first date and the joined meta-data.

Assignees

• Capital One Services Llc

Inventors

• Pham Vincent
• Walters Austin
• Abad Fardin Abdi Taghi
• Taylor Kenneth
• Farivar Reza
• Troung Anh
• Goodsitt Jeremy

Classifications

• G06F18/24765

  Rule-based classification · CPC title

• G06N5/025

  Extracting rules from data · CPC title

• G06F16/122

  using management policies (point-in-time backing up or restoration of persistent data G06F11/1446; file migration policies for HSM systems G06F16/185) · CPC title

• G06F21/6245

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• G06F18/24323

  Tree-organised classifiers · CPC title