Identifying digital private information and preventing privacy violations

Patent metadata

Field	Value
Publication number	US-11264013-B2
Application number	US-201916375197-A
Country	US
Kind code	B2
Filing date	Apr 4, 2019
Priority date	Sep 6, 2018
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

Identifying private information and preventing privacy violations is provided by a process that evaluates digital information obtained by an organization as part of a digital information stream from a user. The evaluating identifies a user utterance, including keyword(s), entity/ies, and intent(s), and applies natural language understanding to the digital information to ascertain a contextual understanding for the user utterance. The process selects training set(s) of historical information from available training sets that includes vocabulary used in varying contexts. The process compares the identified user utterance to an ontology based on the selected training set(s), and determines a confidence level that the digital information includes digital private information. The process also flags for the organization an action to take with respect to handling of the digital information. The flagging is based on the determined confidence level that the digital information includes digital private information.

First claim

What is claimed is:

1. A computer-implemented method comprising:
evaluating digital information obtained by an organization as part of a digital information stream from a user, the evaluating comprising:
identifying a user utterance in the digital information; and
applying natural language understanding to the digital information to ascertain a contextual understanding for the user utterance;

comparing the identified user utterance to an ontology identified based on the ascertained contextual understanding, and determining, based on the comparing, a confidence level that the digital information comprises digital private information; and
performing processing based on the determined confidence level.

2. The method of claim 1 , wherein the confidence level reflects a confidence that the digital information includes at least one selected from the group consisting of: information legally defined to be protected private information, and information considered by the user to be private information.

3. The method of claim 2 , wherein the contextual understanding informs of privacy requirements applicable to the digital information, and wherein a selected training set of historical information, selected based on the ascertained contextual understanding, is reflective of the privacy requirements applicable to the digital information.

4. The method of claim 3 , wherein the contextual understanding for the user utterance includes an understanding of applicable locality of the user, the locality comprising at least one selected from the group consisting of: cultural, language, physical location, moral, social, and mores-based associations of the user.

5. The method of claim 3 , wherein the contextual understanding for the user utterance includes an understanding of legal requirements applicable to retention of the digital information, and wherein the determined confidence level is reflective of a confidence that retaining the digital information falls within a scope of an applicable jurisdictional legal requirement.

6. The method of claim 1 , wherein the determining the confidence level accounts for a situational awareness of the digital information stream, the situational awareness comprising additional information selected from the group consisting of: an audio analysis of audio of the digital information stream, and device measurements from at least one sensor of a device from which the digital information stream is captured.

7. The method of claim 1 , further comprising:
comparing the determined confidence level to a threshold set by the organization; and
selecting an action to take with respect to handling the digital information, the selecting being based on whether the determined confidence level exceeds the threshold.

8. The method of claim 7 , wherein the action selected comprises deleting the digital information.

9. The method of claim 7 , wherein the action selected comprises flagging the digital information for further review by the organization.

10. The method of claim 7 , wherein the action selected comprises raising an alert to the user informing that the digital information comprises digital private information.

11. The method of claim 7 , wherein the action selected comprises retaining the digital information.

12. The method of claim 1 , wherein the comparing comprises classifying the user utterance using a classifier trained from one or more training sets of historical information.

13. The method of claim 1 , wherein the performing processing comprises flagging for the organization an action to take with respect to handling of the digital information, the flagging being based on the determined confidence level that the digital information comprises digital private information, and wherein the method further comprises initiating automatic performance of the flagged action, wherein the flagged action is selected from the group consisting of: deleting the digital information, and archiving the digital information.

14. A computer system comprising:
a memory; and
a processing circuit in communication with the memory, wherein the computer system is configured to perform a method comprising:
evaluating digital information obtained by an organization as part of a digital information stream from a user, the evaluating comprising:
identifying a user utterance in the digital information; and
applying natural language understanding to the digital information to ascertain a contextual understanding for the user utterance;

comparing the identified user utterance to an ontology identified based on the ascertained contextual understanding, and determining, based on the comparing, a confidence level that the digital information comprises digital private information; and
performing processing based on the determined confidence level.

15. The computer system of claim 14 , wherein the confidence level reflects a confidence that the digital information includes at least one selected from the group consisting of: information legally defined to be protected private information, and information considered by the user to be private information, wherein the contextual understanding informs of privacy requirements applicable to the digital information, and wherein the selected training sets are reflective of the privacy requirements applicable to the digital information.

16. The computer system of claim 15 , wherein the contextual understanding for the user utterance includes an understanding of applicable locality of the user, the locality comprising at least one selected from the group consisting of: cultural, language, physical location, moral, social, and mores-based associations of the user.

17. The computer system of claim 14 , wherein the determining the confidence level accounts for a situational awareness of the digital information stream, the situational awareness comprising additional information selected from the group consisting of: an audio analysis of audio of the digital information stream, and device measurements from at least one sensor of a device from which the digital information stream is captured.

18. A computer program product comprising:
a computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
evaluating digital information obtained by an organization as part of a digital information stream from a user, the evaluating comprising:
identifying a user utterance in the digital information; and
applying natural language understanding to the digital information to ascertain a contextual understanding for the user utterance;

comparing the identified user utterance to an ontology identified based on the ascertained contextual understanding, and determining, based on the comparing, a confidence level that the digital information comprises digital private information; and
performing processing based on the determined confidence level.

19. The computer program product of claim 18 , wherein the confidence level reflects a confidence that the digital information includes at least one selected from the group consisting of: information legally defined to be protected private information, and information considered by the user to be private information, wherein the contextual understanding informs of privacy requirements applicable to the digital information, wherein the selected training sets are reflective of the privacy requirements applicable to the digital information, and wherein the contextual understanding for t

Assignees

• Kyndryl Inc

Inventors

• Rudden Mary E
• Perpetua Jr Dennis Anthony
• Freund Bernard

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/228

  of application context · CPC title

• G06F40/279

  Recognition of textual entities · CPC title