Data processing systems for automated classification of personal information from documents and related methods

• US 10,614,247 B2
• Filed: 09/20/2019
• Issued: 04/07/2020
• Est. Priority Date: 06/10/2016
• Status: Active Grant

• Current Assignee: OneTrust LLC
• Original Assignee: OneTrust LLC
• Inventors: Brannon, Jonathan Blake, Jones, Kevin, Patton-Kuhl, Dylan D., Kveen, Bryan Patrick, Pavlichek, Nicholas Ian, Crawford, Eliza Rose, Viswanathan, Subramanian, Shah, Milap
• Primary Examiner(s): Lwin, Maung T
• Application Number:
  US16/577,634
• Publication Number:
  US 20200012814A1
• Time in Patent Office: 200 Days
• Field of Search: None
• CPC Class Codes: G06F 16/215 Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/906 Clustering; Classification
• CPC Class Codes: G06F 21/6245 Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

An automated classification system may be configured to substantially automatically classify one or more pieces of personal information in one or more documents (e.g., one or more text-based documents, one or more spreadsheets, one or more PDFs, one or more webpages, etc.). The system may be implemented in the context of any suitable privacy compliance system, which may, for example, be configured to calculate and assign a sensitivity score to a particular document based at least in part on one or more determined categories of personal information identified in the one or more documents. The storage of particular types of personal information may be governed by one or more government or industry regulations, which may require particular security measures, storage techniques, handling, etc. for documents based on one or more categories of information contained therein.

Claims

1. A computer-implemented data processing method for automatically classifying personal information in an electronic document and generating a sensitivity score for the electronic document based on the classification, the method comprising:

receiving, by one or more processors, the electronic document for analysis;

using one or more natural language processing techniques, by the one or more processors, to decompose data from the electronic document into;

one or more structured objects; and

one or more values for each of the one or more structured objects;

classifying, by the one or more processors, the each of the one or more structured objects in the electronic document based on one or more attributes of the one or more structured objects;

categorizing, by the one or more processors, the each of the one or more structured objects based on a sensitivity of the one or more structured objects;

rating, by the one or more processors, an accuracy of the categorization, wherein rating the accuracy of the categorization comprises;

receiving a second electronic document that is related to the electronic document;

using the one or more natural language processing techniques, by one or more processors, to decompose data from the second electronic document into;

one or more second structured objects; and

one or more second values for each of the one or more structured objects;

classifying, by one or more processors, each of the one or more second structured objects in the second electronic document based on one or more second attributes of the one or more second structured objects;

categorizing, by one or more processors, each of the one or more second structured objects based on a sensitivity of the one or more second structured objects; and

comparing the categorization of the one or more structured objects with the categorization of the one or more second structured objects; and

rating the accuracy based on the comparison; and

generating, by the one or more processors, a sensitivity score for the electronic document based at least in part on the categorized one or more structured objects and the associated one or more values.

2. The computer-implemented data processing method of claim 1, wherein generating the sensitivity score for the electronic document comprises:

assigning a relative sensitivity rating to the each of the one or more structured objects; and

calculating the sensitivity score based on the one or more values and the relative sensitivity rating for the each of the one or more structured objects.

3. The computer-implemented data processing method of claim 1, wherein the one or more natural language processing techniques comprises at least one technique selected from a group consisting of:

one or more optical character recognition techniques; and

one or more audio processing techniques.

4. The computer-implemented data processing method of claim 1, wherein the one or more attributes of the one or more structured objects comprise a position within the electronic document of each of the one or more structured objects in the electronic document.

5. The computer-implemented data processing method of claim 1, wherein the sensitivity of the one or more structured objects is automatically determined based at least in part on one or more government regulations directed toward the type of information associated with a particular one or more structured objects.

6. The computer-implemented data processing of claim 1, wherein rating the accuracy of the categorization of each of the one or more structured objects further comprises:

determining a character type for each of the one or more structured objects;

determining a character type for each value associated with each of the one or more structured objects;

comparing the character type for each value associated with each of the one or more structured objects and the character type for each of the one or more structured objects; and

rating the accuracy of the categorization of each of the one or more structured objects based at least in part on comparing the character type for each value associated with each of the one or more structured objects and the character type for each of the one or more structured objects.

7. A computer-implemented data processing method for automatically classifying personal information in an electronic document and generating a sensitivity score for the electronic document based on the classification, the method comprising:

receiving, by one or more processors, the electronic document for analysis;

sorting, using one or more natural language processing techniques, data from the electronic document into;

one or more structured objects; and

one or more values for each of the one or more structured objects;

classifying, by the one or more processors, the each of the one or more structured objects in the electronic document based on one or more attributes of the one or more structured objects;

categorizing, by the one or more processors, the each of the one or more structured objects based on a sensitivity of the one or more structured objects;

generating, by the one or more processors, a sensitivity score for the electronic document based at least in part on the categorized one or more structured objects and the associated one or more values;

parsing the classification of one or more structured objects;

identifying the each of the one or more structured objects having an empty associated value;

modifying the classification of one or more structured objects to remove the identified one or more structured objects from the classification;

rating, by the one or more processors, an accuracy of the categorization by receiving a second electronic document that is related to the electronic document;

sorting, using the one or more natural language processing techniques, the second electronic document into;

one or more second structured objects; and

one or more second values for each of the one or more structured objects;

classifying, by the one or more processors, each of the one or more second structured objects in the second electronic document based on one or more second attributes of the one or more second structured objects;

categorizing, by the one or more processors, each of the one or more second structured objects based on a sensitivity of the one or more second structured objects; and

generating, by the one or more processors, a second sensitivity score for the second electronic document based at least in part on the categorized one or more second structured objects and the associated one or more second values;

parsing the classification of one or more second structured objects;

identifying each of the one or more second structured objects having an empty associated value;

modifying the classification of one or more second structured objects to remove the identified one or more second structured objects from the classification;

comparing the categorization of the one or more structured objects with the categorization of the one or more second structured objects; and

rating the accuracy based on the comparison.

8. The computer-implemented data processing method of claim 7, wherein generating the sensitivity score for the electronic document comprises:

assigning a relative sensitivity rating to the each of the one or more structured objects; and

calculating the sensitivity score based on the one or more values and the relative sensitivity rating for the each of the one or more structured objects.

9. The computer-implemented data processing method of claim 7, wherein the one or more natural language processing techniques comprise at least one technique selected from a group consisting of:

one or more optical character recognition techniques; and

one or more audio processing techniques.

10. The computer-implemented data processing method of claim 7, wherein the one or more attributes of the one or more structured objects comprise a position within the electronic document of each of the one or more structured objects in the electronic document.

11. The computer-implemented data processing method of claim 7, wherein the sensitivity of the one or more structured objects is automatically determined based at least in part on one or more government regulations directed toward the type of information associated with a particular one or more structured objects.

12. A computer-implemented data processing method for automatically classifying personal information in an electronic document and generating a sensitivity score for the electronic document based on the classification, the method comprising:

receiving, by one or more processors, the electronic document for analysis;

using one or more natural language processing techniques, by the one or more processors, to decompose data from the electronic document into;

one or more structured objects; and

one or more values for each of the one or more structured objects;

classifying, by the one or more processors, the each of the one or more structured objects in the electronic document based on one or more attributes of the one or more structured objects;

categorizing, by the one or more processors, the each of the one or more structured objects based on a sensitivity of the one or more structured objects;

generating, by the one or more processors, a sensitivity score for the electronic document based at least in part on the categorized one or more structured objects and the associated one or more values;

rating an accuracy of the categorization by receiving a second electronic document that is related to the electronic document;

using the one or more natural language processing techniques, by the one or more processors, to decompose data from the second electronic document into;

one or more second structured objects; and

one or more second values for each of the one or more structured objects;

classifying, by the one or more processors, each of the one or more second structured objects in the second electronic document based on one or more second attributes of the one or more second structured objects;

categorizing, by the one or more processors, the each of the one or more second structured objects based on a sensitivity of the one or more second structured objects; and

comparing the categorization of the one or more structured objects with the categorization of the one or more second structured objects; and

rating the accuracy based on the comparison.

13. The computer-implemented data processing method of claim 12, wherein generating the sensitivity score for the electronic document comprises:

assigning a relative sensitivity rating to the each of the one or more structured objects; and

calculating the sensitivity score based on the one or more values and the relative sensitivity rating for the each of the one or more structured objects.

14. The computer-implemented data processing method of claim 12, wherein the one or more natural language processing techniques comprise one or more optical character recognition techniques.

15. The computer-implemented data processing method of claim 12, wherein the one or more attributes of the one or more structured objects comprise a position within the electronic document of each of the one or more structured objects in the electronic document.

16. The computer-implemented data processing method of claim 12, wherein the sensitivity of the one or more structured objects is automatically determined based at least in part on one or more government regulations directed toward the type of information associated with a particular one or more structured objects.