IP Library Granted Patent US 11,275,855
Granted Patent B2
US 11,275,855 · App. 16/038,886 · Granted Mar 15, 2022

Conversation print system and method

Inventor: Haydar Talib (Montreal, CA)
Assignee: NUANCE COMMUNICATIONS, INC.
G06F21/608G06F21/32G06Q50/265G10L15/1807G10L15/26G10L15/32G10L17/00G10L17/06H04M3/2218H04M3/2281H04M3/42221G06F2221/2115H04M2203/6027
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 11,275,855
App. No.
16/038,886
Granted
Mar 15, 2022
Kind
B2
Abstract

A method, computer program product, and computing system for defining a conversation print for each of a plurality of known fraudsters, thus defining a plurality of fraudster conversation prints. The plurality of fraudster conversation prints is processed to identify one or more fraudster commonalities. A fraudster conversation template is generated based, at least in part, upon the one or more fraudster commonalities.

Claims (57)

1. A computer-implemented method, executed on a computing device, comprising:

defining a conversation print for each of a plurality of known fraudsters, thus defining a plurality of fraudster conversation prints, wherein the conversation print includes a text-based transcript of voice-based content received from at least one known fraudster of the plurality of known fraudsters, and wherein the conversation print defines speech-pattern indicia that includes frequency of only a single word chosen and used by the at least one known fraudster over a similar single word chosen and used by another person, and wherein the conversation print further defines speech-pattern indicia that includes one or more inflection patterns defined within the voice-based content, wherein the one or more inflection patterns include a location of one or more inflections in one or more sentences, wherein the conversation print is further based upon, at least in part, one or more pause patterns, speech speed patterns, word character length patterns, and filler word patterns of the one or more pause patterns defined within the voice-based content;

processing the plurality of fraudster conversation prints, including the one or more inflection patterns, the location of one or more inflections in one or more sentences, the speech speed patterns, the one or more pause patterns, the word character length patterns, and the filler word patterns of the one or more pause patterns of the voice-based content, to identify one or more fraudster commonalities; and

generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities;

determining if a call includes a fraudster of the plurality of known fraudsters based upon the fraudster conversation template;

continuing the call if the call does not include the fraudster; and

taking remedial action if the call does include the fraudster, wherein remedial action includes at least one of terminating the call and providing a notification that the call does include the fraudster.

2. The computer-implemented method of claim 1 wherein the one or more fraudster commonalities includes one or more of:

one or more common stories;

one or more common words;

one or more common phrases;

one or more common talking points; and

one or more common themes.

3. The computer-implemented method of claim 2 wherein generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities includes:

generating a fraudster conversation template based, at least in part, upon the one or more of: the one or more common stories, the one or more common words, the one or more common phrases, the one or more common talking points; and the one or more common themes.

4. The computer-implemented method of claim 1 wherein each conversation print defines speech-pattern indicia that includes:

one or more accent patterns defined within the voice-based content.

5. The computer-implemented method of claim 1 wherein each conversation print defines speech-pattern indicia that includes:

one or more word choice patterns defined within the voice-based content.

6. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:

defining a conversation print for each of a plurality of known fraudsters, thus defining a plurality of fraudster conversation prints, wherein the conversation print includes a text-based transcript of voice-based content received from at least one known fraudster of the plurality of known fraudsters, and wherein the conversation print defines speech-pattern indicia that includes frequency of only a single word chosen and used by the at least one known fraudster over a similar single word chosen and used by another person, and wherein the conversation print further defines speech-pattern indicia that includes one or more inflection patterns defined within the voice-based content, wherein the one or more inflection patterns include a location of one or more inflections in one or more sentences, wherein the conversation print is further based upon, at least in part, one or more pause patterns, speech speed patterns, word character length patterns, and filler word patterns of the one or more pause patterns defined within the voice-based content;

processing the plurality of fraudster conversation prints, including the one or more inflection patterns, the location of one or more inflections in one or more sentences, the speech speed patterns, the one or more pause patterns, the word character length patterns, and the filler word patterns of the one or more pause patterns of the voice-based content, to identify one or more fraudster commonalities; and

generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities;

determining if a call includes a fraudster of the plurality of known fraudsters based upon the fraudster conversation template;

continuing the call if the call does not include the fraudster; and

taking remedial action if the call does include the fraudster, wherein remedial action includes at least one of terminating the call and providing a notification that the call does include the fraudster.

7. The computer program product of claim 6 wherein the one or more fraudster commonalities includes one or more of:

one or more common stories;

one or more common words;

one or more common phrases;

one or more common talking points; and

one or more common themes.

8. The computer program product of claim 7 wherein generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities includes:

generating a fraudster conversation template based, at least in part, upon the one or more of: the one or more common stories, the one or more common words, the one or more common phrases, the one or more common talking points; and the one or more common themes.

9. The computer program product of claim 6 wherein each conversation print defines speech-pattern indicia that includes:

one or more accent patterns defined within the voice-based content.

10. The computer program product of claim 6 wherein each conversation print defines speech-pattern indicia that includes:

one or more word choice patterns defined within the voice-based content.

11. A computing system including a processor and memory configured to perform operations comprising:

defining a conversation print for each of a plurality of known fraudsters, thus defining a plurality of fraudster conversation prints, wherein the conversation print includes a text-based transcript of voice-based content received from at least one known fraudster of the plurality of known fraudsters, and wherein the conversation print defines speech-pattern indicia that includes frequency of only a single word chosen and used by the at least one known fraudster over a similar single word chosen and used by another person, and wherein the conversation print further defines speech-pattern indicia that includes one or more inflection patterns defined within the voice-based content, wherein the one or more inflection patterns include a location of one or more inflections in one or more sentences, wherein the conversation print is further based upon, at least in part, one or more pause patterns, speech speed patterns, word character length patterns, and filler word patterns of the one or more pause patterns defined within the voice-based content;

processing the plurality of fraudster conversation prints, including the one or more inflection patterns, the location of one or more inflections in one or more sentences, the speech speed patterns, the one or more pause patterns, the word character length patterns, and the filler word patterns of the one or more pause patterns of the voice-based content, to identify one or more fraudster commonalities; and

generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities;

determining if a call includes a fraudster of the plurality of known fraudsters based upon the fraudster conversation template;

continuing the call if the call does not include the fraudster; and

taking remedial action if the call does include the fraudster, wherein remedial action includes at least one of terminating the call and providing a notification that the call does include the fraudster.

12. The computing system of claim 11 wherein the one or more fraudster commonalities includes one or more of:

one or more common stories;

one or more common words;

one or more common phrases;

one or more common talking points; and

one or more common themes.

13. The computing system of claim 12 wherein generating a fraudster conversation template based, at least in part, upon the one or more fraudster commonalities includes:

generating a fraudster conversation template based, at least in part, upon the one or more of: the one or more common stories, the one or more common words, the one or more common phrases, the one or more common talking points; and the one or more common themes.

14. The computing system of claim 11 wherein each conversation print defines speech-pattern indicia that includes:

one or more accent patterns defined within the voice-based content.

15. The computing system of claim 11 wherein each conversation print defines speech-pattern indicia that includes:

one or more word choice patterns defined within the voice-based content.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 9, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065530/0871 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 3, 2018
From: TALIB, HAYDAR
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 046547/0095 →