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

Patent metadata

Field	Value
Publication number	US-12461946-B2
Application number	US-202418753343-A
Country	US
Kind code	B2
Filing date	Jun 25, 2024
Priority date	Nov 1, 2019
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

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 data security standard compliant dataset and a data security standard non-compliant dataset, the meta-data including a first date at which the data security standard compliant dataset became compliant against a first set of privacy standard rules; joining the meta-data from the data security standard compliant dataset and the meta-data from the data security standard non-compliant dataset to create a set of estimated rules; marking an unknown data security standard compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on the set of estimated rules; and modifying a marked non-compliant data security standard compliance dataset by automatically removing or adding one or more elements based on the joined meta-data to render the marked non-compliant data security standard compliance dataset compliant.

2 . The non-transitory computer-accessible medium of claim 1 , further comprising creating the set of estimated rules based on the first date.

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

4 . The non-transitory computer-accessible medium of claim 3 , 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.

5 . The non-transitory computer-accessible medium of claim 1 , wherein the set of estimated rules are generated by a machine learning algorithm.

6 . The non-transitory computer-accessible medium of claim 5 , wherein the set of estimated rules is based on the machine learning algorithm learning a plurality of compliant and non-compliant features in the meta-data.

7 . The non-transitory computer-accessible medium of claim 5 , wherein the machine learning algorithm is a random forest learning algorithm.

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

9 . 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.

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

11 . 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.

12 . A method, comprising:
obtaining meta-data from a data security standard compliant dataset and a data security standard non-compliant dataset, the meta-data including a first date at which the data security standard compliant dataset became compliant against a first set of privacy standard rules; joining the meta-data from the data security standard compliant dataset and the meta-data from the data security standard non-compliant dataset to create a set of estimated rules; marking an unknown data security standard compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on the set of estimated rules; and modifying a marked non-compliant data security standard compliance dataset by automatically removing or adding one or more elements based on the joined meta-data to render the marked non-compliant data security standard compliance dataset compliant.

13 . The method of claim 12 , further comprising generating the set of estimated rules based on the first date and the joined meta-data.

14 . The method of claim 13 , wherein the set of estimated rules are generated by a machine learning algorithm.

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

16 . The method of claim 15 , 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.

17 . The method of claim 12 , further comprising appending additional data to the compliant dataset and re-verifying the appended dataset.

18 . The method of claim 12 , 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.

19 . The method of claim 12 , further comprising generating a list of rules against which a set of data is compliant.

20 . A system, comprising:
a computer hardware arrangement consisting of at least a processor and memory, configured to:
obtain meta-data from a data security standard compliant dataset and a data security standard non-compliant dataset, the meta-data including a first date at which the data security standard compliant dataset became compliant against a first set of privacy standard rules;
join the meta-data from the data security standard compliant dataset and the meta-data from the data security standard non-compliant dataset to create a set of estimated rules;
mark an unknown data security standard compliance dataset as compliant or non-compliant with respect to at least one set of unknown time-variable rules based on the set of estimated rules; and
modify a marked non-compliant data security standard compliance dataset by automatically removing or adding one or more elements based on the joined meta-data to render the marked non-compliant data security standard compliance dataset compliant.

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