IP Library › Granted Patent US 11,263,663
Granted Patent B2
US 11,263,663 · App. 16/509,248 · Granted Mar 1, 2022

Intercepting inadvertent conversational disclosure of personal information

Inventors: Daniel M. Gruen (Newton, MA); Nicola Palmarini (Boston, MA); Olivia Choudhury (Cambridge, MA); Panagiotis Karampourniotis (Cambridge, MA); Issa Sylla (Boston, MA); Morgan Foreman (Cambridge, MA)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06Q30/0248G06F40/30G06N5/047G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,263,663
App. No.
16/509,248
Granted
Mar 1, 2022
Kind
B2
Abstract

By intercepting a natural language communication of a protected party, the communication is monitored, wherein the protected party is a human being. Within the monitored communication using a natural language processing engine, a natural language interaction between the protected party and a second party is detected. To determine an interaction pattern, the natural language interaction is analyzed. The interaction pattern includes data derived from the monitored communication, metadata of the protected party, and metadata of the second party. Using the interaction pattern and an interaction behavior model, an adverse result of the natural language interaction is predicted, wherein the adverse result comprises an economic loss to the protected party. By notifying the protected party, the predicted adverse result is intercepted.

Claims (41)

1. A computer-implemented method comprising:

monitoring, by intercepting a network-mediated natural language communication of a protected party, the communication;

detecting, within the monitored communication using a natural language processing engine, a natural language interaction including the protected party;

analyzing, to determine an interaction pattern, the natural language interaction, the interaction pattern comprising data derived from the monitored communication, metadata of the protected party, and metadata of a recipient of the monitored communication;

predicting, using the interaction pattern and an interaction behavior model, a disclosure of personal information of the protected party, the disclosure predicted to be performed by the protected party during a future portion of the natural language interaction; and

preventing, by muting a microphone of the protected party, a communication of the protected party, the communication predicted to contain the disclosure.

2. The computer-implemented method of claim 1 , wherein the interaction behavior model comprises a set of rules, a rule in the set of rules comprising an interaction pattern predictive of an adverse result.

3. The computer-implemented method of claim 2 , wherein the interaction behavior model further comprises a set of exceptions, an exception in the set of exceptions comprising an interaction pattern for which a rule in the set of rules does not apply.

4. The computer-implemented method of claim 1 , wherein the interaction behavior model comprises a learning model, the learning model trained to recognize an interaction pattern predictive of the disclosure.

5. The computer-implemented method of claim 4 , wherein the learning model is further trained using the interaction pattern and a previous disclosure of the protected party.

6. The computer-implemented method of claim 1 , further comprising:

analyzing, to determine a second interaction pattern, a second natural language interaction including the protected party, the second natural language interaction excluding a party to the natural language interaction;

predicting, using the second interaction pattern and the interaction behavior model, a second disclosure of personal information of the protected party during a future portion of the second natural language interaction; and

analyzing, to generate trend data of the protected party, the interaction pattern, the predicted disclosure, the second interaction pattern, and the second predicted disclosure.

7. The computer-implemented method of claim 6 , further comprising:

generating, responsive to a portion of the trend data being outside of a threshold range of values, a trend alert.

8. A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:

program instructions to monitor, by intercepting a network-mediated natural language communication of a protected party, the communication;

program instructions to detect, within the monitored communication using a natural language processing engine, a natural language interaction including the protected party;

program instructions to analyze, to determine an interaction pattern, the natural language interaction, the interaction pattern comprising data derived from the monitored communication, metadata of the protected party, and metadata of a recipient of the monitored communication;

program instructions to predict, using the interaction pattern and an interaction behavior model, a disclosure of personal information of the protected party, the disclosure predicted to be performed by the protected party during a future portion of the natural language interaction; and

program instructions to prevent, by muting a microphone of the protected party, a communication of the protected party, the communication predicted to contain the disclosure.

9. The computer usable program product of claim 8 , wherein the interaction behavior model comprises a set of rules, a rule in the set of rules comprising an interaction pattern predictive of an adverse result.

10. The computer usable program product of claim 9 , wherein the interaction behavior model further comprises a set of exceptions, an exception in the set of exceptions comprising an interaction pattern for which a rule in the set of rules does not apply.

11. The computer usable program product of claim 8 , wherein the interaction behavior model comprises a learning model, the learning model trained to recognize an interaction pattern predictive of the disclosure.

12. The computer usable program product of claim 11 , wherein the learning model is further trained using the interaction pattern and a previous disclosure of the protected party.

13. The computer usable program product of claim 8 , further comprising:

program instructions to analyze, to determine a second interaction pattern, a second natural language interaction including the protected party, the second natural language interaction excluding a party to the natural language interaction;

program instructions to predict, using the second interaction pattern and the interaction behavior model, a second disclosure of personal information of the protected party during a future portion of the second natural language interaction; and

program instructions to analyze, to generate trend data of the protected party, the interaction pattern, the predicted disclosure, the second interaction pattern, and the second predicted disclosure.

14. The computer usable program product of claim 13 , further comprising:

program instructions to generate, responsive to a portion of the trend data being outside of a threshold range of values, a trend alert.

15. The computer usable program product of claim 8 , wherein the computer usable code is stored in a computer readable storage device in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system.

16. The computer usable program product of claim 8 , wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

17. A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

program instructions to monitor, by intercepting a network-mediated natural language communication of a protected party, the communication;

program instructions to detect, within the monitored communication using a natural language processing engine, a natural language interaction including the protected party;

program instructions to analyze, to determine an interaction pattern, the natural language interaction, the interaction pattern comprising data derived from the monitored communication, metadata of the protected party, and metadata of a recipient of the monitored communication;

program instructions to predict, using the interaction pattern and an interaction behavior model, a disclosure of personal information of the protected party, the disclosure predicted to be performed by the protected party during a future portion of the natural language interaction; and

program instructions to prevent, by muting a microphone of the protected party, a communication of the protected party, the communication predicted to contain the disclosure.

18. The computer system of claim 17 , wherein the interaction behavior model comprises a set of rules, a rule in the set of rules comprising an interaction pattern predictive of an adverse result.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2019
From: GRUEN, DANIEL M.; PALMARINI, NICOLA; CHOUDHURY, OLIVIA; KARAMPOURNIOTIS, PANAGIOTIS; SYLLA, ISSA; FOREMAN, MORGAN
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 049736/0631 →
Continuity (1)
Related Publication 20210012374A1 · Jan 14, 2021
Cited By (1)
US 12,367,344