Method and apparatus for template-based processing of electronic documents

• US 9,208,450 B1
• Filed: 08/26/2013
• Issued: 12/08/2015
• Est. Priority Date: 09/26/2008
• Status: Active Grant

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Symantec Corporation (NortonLifeLock Inc.)
• Inventors: Kabra, Navin, Rajan, Basant, Nanda, Bijayalaxmi
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US14/010,240
• Time in Patent Office: 834 Days
• Field of Search: 707600-831, 707/899, 707999001-999206
• US Class Current: 1/1
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Techniques for processing electronic documents are disclosed. In one particular embodiment, the techniques may be realized as a method for processing electronic documents comprising obtaining an electronic document being sent over a network toward a destination, analyzing text content of the electronic documents to identify whether the electronic document matches any of a plurality of predefined document templates, wherein the electronic document conforms to a structure of at least one of the plurality of predefined document templates, and wherein the analyzing comprises executing at least one machine learning algorithm, the at least one machine learning algorithm trained using at least one sample electronic document having a predefined template, obtaining a document loss prevention (DLP) policy based on the at least one document template associated with the electronic document, and selectively allowing the electronic document to continue toward the destination based on the DLP policy.

Claims

1. A method for processing electronic documents comprising:

obtaining an electronic document being sent over a network toward a destination;

analyzing text content of the electronic documents to identify whether the electronic document matches any of a plurality of predefined document templates, wherein the electronic document conforms to a structure of at least one of the plurality of predefined document templates, and wherein the analyzing comprises executing at least one machine learning algorithm, the at least one machine learning algorithm trained using at least one sample electronic document having a predefined template;

obtaining a document loss prevention (DLP) policy based on the at least one predefined document template associated with the electronic document, wherein the DLP policy defines at least one rule to block sending of at least one of the electronic documents if the at least one of the electronic documents matches any of the plurality of predefined document templates; and

selectively allowing the electronic document to continue toward the destination based on the DLP policy.

2. The method of claim 1, wherein the electronic document is obtained from an electronic mail message, and wherein the destination is represented by an electronic mail address.

3. The method of claim 2, further comprising sending a notification to an originator of the electronic mail message if the electronic document is not allowed to continue toward the destination based on the DLP policy.

4. The method of claim 1, wherein the at least one machine learning algorithm is responsive to text constructs in the text content of the electronic document to identify whether the electronic document matches any of the plurality of predefined document templates.

5. The method of claim 1, wherein the plurality of predefined document templates were generated based on one or more predefined rules.

6. The method of claim 1, further comprising analyzing a predefined native document template of the electronic document to identify whether the predefined native template thereof matches any of a plurality of predefined document templates.

7. The method of claim 1, wherein the DLP policy defines a set of destinations associated with the at least one predefined document template, and wherein the electronic document is not allowed to continue to any destination in the set of destinations.

8. A system for processing electronic documents comprising:

one or more processors communicatively coupled to a network, wherein the one or more processors are configured to;

obtain an electronic document being sent over a network toward a destination;

analyze text content of the electronic documents to identify whether the electronic document matches any of a plurality of predefined document templates, wherein the electronic document conforms to a structure of at least one of the plurality of predefined document templates, and wherein the analyzing comprises executing at least one machine learning algorithm, the at least one machine learning algorithm trained using at least one sample electronic document having a predefined template;

obtain a document loss prevention (DLP) policy based on the at least one predefined document template associated with the electronic document, wherein the DLP policy defines at least one rule to block sending of at least one of the electronic documents if the at least one of the electronic documents matches any of the plurality of predefined document templates; and

selectively allow the electronic document to continue toward the destination based on the DLP policy.

9. The system of claim 8, wherein the electronic document is obtained from an electronic mail message, and wherein the destination is represented by an electronic mail address.

10. The system of claim 9, wherein the one or more processors are further configured to send a notification to an originator of the electronic mail message if the electronic document is not allowed to continue toward the destination based on the DLP policy.

11. The system of claim 8, wherein the at least one machine learning algorithm is responsive to text constructs in the text content of the electronic document to identify whether the electronic document matches any of the plurality of predefined document templates.

12. The system of claim 8, wherein the plurality of predefined document templates were generated based on one or more predefined rules.

13. The system of claim 8, wherein the one or more processors are further configured to analyze a predefined native document template of the electronic document to identify whether the predefined native template thereof matches any of a plurality of predefined document templates.

14. The system of claim 8, wherein the DLP policy defines a set of destinations associated with the at least one predefined document template, and wherein the electronic document is not allowed to continue to any destination in the set of destinations.

15. An article of manufacture for processing electronic documents, the article of manufacture comprising:

at least one non-transitory processor readable storage medium; and

instructions stored on the at least one medium;

wherein the instructions are configured to be readable from the at least one medium by at least one processor and thereby cause the at least one processor to operate so as to;

obtain an electronic document being sent over a network toward a destination;

analyze text content of the electronic documents to identify whether the electronic document matches any of a plurality of predefined document templates, wherein the electronic document conforms to a structure of at least one of the plurality of predefined document templates, and wherein the analyzing comprises executing at least one machine learning algorithm, the at least one machine learning algorithm trained using at least one sample electronic document having a predefined template;

obtain a document loss prevention (DLP) policy based on the at least one predefined document template associated with the electronic document, wherein the DLP policy defines at least one rule to block sending of at least one of the electronic documents if the at least one of the electronic documents matches any of the plurality of predefined document templates; and

selectively allow the electronic document to continue toward the destination based on the DLP policy.

16. The article of manufacture of claim 15, wherein the electronic document is obtained from an electronic mail message, and wherein the destination is represented by an electronic mail address.

17. The article of manufacture of claim 15, wherein the instructions are further configured to cause the at least one processor to operate further so as to send a notification to an originator of the electronic mail message if the electronic document is not allowed to continue toward the destination based on the DLP policy.

18. The article of manufacture of claim 15, wherein the at least one machine learning algorithm is responsive to text constructs in the text content of the electronic document to identify whether the electronic document matches any of the plurality of predefined document templates.

19. The article of manufacture of claim 15, wherein the instructions are further configured to cause the at least one processor to operate further so as to analyze a predefined native document template of the electronic document to identify whether the predefined native template thereof matches any of a plurality of predefined document templates.

20. The article of manufacture of claim 15, wherein the DLP policy defines a set of destinations associated with the at least one predefined document template, and wherein the electronic document is not allowed to continue to any destination in the set of destinations.