IP Library › Granted Patent US 11,107,006
Granted Patent B2
US 11,107,006 · App. 16/868,169 · Granted Aug 31, 2021

Visualization, exploration and shaping conversation data for artificial intelligence-based automated interlocutor training

Inventor: Jonathan E. Eisenzopf (San Francisco, CA)
Assignee: discourse.ai, Inc.
G06N20/00G06N3/006G06N5/04G10L15/1815G10L15/22H04L51/02G06Q30/016G10L2015/223
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 11,107,006
App. No.
16/868,169
Granted
Aug 31, 2021
Kind
B2
Abstract

A system and method for visualizing, exploring and shaping conversational data within a corpus for selective export to train an artificial intelligence-based interlocutor platform, which includes selecting, according to user inputs, a plurality of the conversations for generation of an interactive radial space-filling sunburst-style diagram; responsive to user navigation controls, revising the sunburst diagram to allow provide selection, filtering and modification of the of the text-based interlocutory conversations; and, according to user export controls, formatting and saving at least a portion of the selected and filtered plurality of text-based interlocutory conversations into training data for an artificial intelligence-based automated interlocutor platform.

Claims (38)

1. A method implemented by a computing device for visualizing, exploring and shaping conversational data within a corpus for selective export to train an artificial intelligence-based interlocutor platform, the method comprising:

selecting, by a computer processor, according to one or more diagram generation command user inputs, a plurality of text-based interlocutory conversations from the conversational data; and

generating, by a computer processor, a graphical user interface using the selected plurality of text-based interlocutory conversations, in which:

one or more conversational flows are depicted on a computer display as a series of sequentially adjacent blocks in a radial space-filling sunburst-style diagram;

responsive to one or more received user interactive navigation inputs, generating, revising and displaying on a computer display the radial space-filling sunburst-style diagram to select, filter and modify the selected plurality of the text-based interlocutory conversations; and

according to one or more received user export selections inputs, formatting and saving, by a computer processor, a portion of the selected and filtered plurality of text-based interlocutory conversations into training data for an artificial intelligence-based automated interlocutor platform.

2. The method of claim 1 wherein the generating of the radial space-filling sunburst-style diagram further comprises generating, rendering and displaying, on the computer display, by the computer processor, a conversational flow ribbon depicting a series of conversation elements according to the one or more received user interactive navigation inputs.

3. The method of claim 2 wherein the conversational flow ribbon comprises two or more elements selected from the group consisting of intents, goals, turns, slots and dialogs.

4. The method of claim 3 wherein the generating of the radial space-filling sunburst-style diagram further comprises generating, rendering and displaying, on the computer display, by the computer processor, of a collection of conversational flow ribbons.

5. The method of claim 3 wherein the generating of the radial space-filling sunburst-style diagram further comprises generating, rendering and displaying, on the computer display, by the computer processor, one or more user controls to modify one or more elements of a conversational flow ribbon.

6. The method of claim 4 wherein the generating of the radial space-filling sunburst-style diagram further comprises generating, rendering and displaying, on the computer display, by the computer processor, one or more user controls to modify the collection of conversational flow ribbons.

7. A computer program product for visualizing, exploring and shaping conversational data within a corpus for selective export to train an artificial intelligence-based interlocutor platform, the computer program product comprising:

one or more computer-readable memory devices which is not a propagating signal, carrier wave or transmission medium per se; and

computer-executable instructions encoded by the one or more computer-readable memory devices which, when executed by a computer processor, causes a computer to:

select, according to one or more diagram generation command user inputs, a plurality of text-based interlocutory conversations from the conversational data; and

generate a graphical user interface using the selected plurality of text-based interlocutory conversations, in which:

one or more conversational flows are depicted on a computer display as a series of sequentially adjacent blocks in a radial space-filling sunburst-style diagram;

responsive to one or more received user interactive navigation inputs, generating, revising and displaying on a computer display the radial space-filling sunburst-style diagram to select, filter and modify the selected plurality of the text-based interlocutory conversations; and

according to one or more received user export selections inputs, format and save a portion of the selected and filtered plurality of text-based interlocutory conversations into training data for an artificial intelligence-based automated interlocutor platform.

8. The computer program product of claim 7 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, a conversational flow ribbon depicting a series of conversation elements according to the one or more received user interactive navigation inputs.

9. The computer program product of claim 8 wherein the conversational flow ribbon comprises two or more elements selected from the group consisting of intents, goals, turns, slots and dialogs.

10. The computer program product of claim 9 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, of a collection of conversational flow ribbons.

11. The computer program product of claim 9 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, one or more user controls to modify one or more elements of a conversational flow ribbon.

12. The computer program product of claim 10 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, one or more user controls to modify the collection of conversational flow ribbons.

13. A system for visualizing, exploring and shaping conversational data within a corpus for selective export to train an artificial intelligence-based interlocutor platform, the system comprising:

one or more computer processors;

one or more computer-readable memory devices which is not a propagating signal, carrier wave or transmission medium per se; and

computer-executable instructions encoded by the one or more computer-readable memory devices which, when executed by the one or more computer processors, causes one or more computers to:

select, according to one or more diagram generation command user inputs, a plurality of text-based interlocutory conversations from the conversational data; and

generate a graphical user interface using the selected plurality of text-based interlocutory conversations, in which:

one or more conversational flows are depicted on a computer display as a series of sequentially adjacent blocks in a radial space-filling sunburst-style diagram;

responsive to one or more received user interactive navigation inputs, generating, revising and displaying on a computer display the radial space-filling sunburst-style diagram to select, filter and modify the selected plurality of the text-based interlocutory conversations; and

according to one or more received user export selections inputs, format and save a portion of the selected and filtered plurality of text-based interlocutory conversations into training data for an artificial intelligence-based automated interlocutor platform.

14. The system of claim 13 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, a conversational flow ribbon depicting a series of conversation elements according to the one or more received user interactive navigation inputs.

15. The system of claim 14 wherein the conversational flow ribbon comprises two or more elements selected from the group consisting of intents, goals, turns, slots and dialogs.

16. The system of claim 15 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, of a collection of conversational flow ribbons.

17. The system of claim 15 wherein the instructions for generating of the sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, one or more user controls to modify one or more elements of a conversational flow ribbon.

18. The system of claim 16 wherein the computer-executable instructions for generating of the radial space-filling sunburst-style diagram further comprise instructions for generating, rendering and displaying, on the computer display, one or more user controls to modify the collection of conversational flow ribbons.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 6, 2020
From: EISENZOPF, JONATHAN E
To: DISCOURSE.AI, INC.
Reel/Frame 052590/0417 →
Continuity (7)
Continuation In Part 16786923 · Feb 10, 2020
Continuation 16734973 · Jan 6, 2020
Continuation In Part 16201188 · Nov 27, 2018
Continuation In Part 16210081 · Dec 5, 2018
Provisional Application 62594610 · Dec 5, 2017
Provisional Application 62594616 · Dec 5, 2017
Related Publication 20200265339A1 · Aug 20, 2020
Cited By (3)
US 12,271,706 US 12,561,530 US 12,651,124