IP Library Granted Patent US 11,095,579
Granted Patent B1
US 11,095,579 · App. 16/875,420 · Granted Aug 17, 2021

Chatbot with progressive summary generation

Inventors: Hugues Sézille de Mazancourt (Thiais, FR); Alain Kaeser (Paris, FR)
Assignee: YSEOP SA
H04L51/02G06F40/40H04L51/16
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 11,095,579
App. No.
16/875,420
Granted
Aug 17, 2021
Kind
B1
Abstract

Methods and apparatus for summarizing a chatbot interaction with a user are provided. The method comprises using at least one computer hardware processor to perform generating an initial summary based, at least in part, on user data, receiving first input from the user during the chatbot interaction, processing the first input with a natural language processing engine, updating the initial summary based, at least in part, on an output of the processing by the natural language processing engine to generate an updated summary, wherein the updating is performed prior to completion of the chatbot interaction, and outputting a final summary of the chatbot interaction, wherein the final summary of the chatbot interaction is based, at least in part, on the updated summary.

Claims (61)

1. A method of summarizing a chatbot interaction with a first user, the method comprising:

using at least one computer hardware processor to perform:

receiving user data of the first user via a network from at least one application executing on at least one computer;

generating an initial summary based, at least in part, on the received user data of the first user;

receiving first input from the first user during the chatbot interaction;

processing the first input with a natural language processing engine;

updating the initial summary based, at least in part, on an output of the processing by the natural language processing engine to generate an updated summary, wherein the updating is performed prior to completion of the chatbot interaction; and

outputting a final summary of the chatbot interaction, wherein the final summary of the chatbot interaction is based, at least in part, on the updated summary,

wherein outputting the final summary of the chatbot interaction comprises providing the final summary of the chatbot interaction to the at least one application executing on the at least one computer, the at least one application enabling, at least in part, a second user to follow up with the first user to schedule and/or complete, based, at least in part, on the final summary, a service or transaction mentioned during the chatbot interaction.

2. The method of claim 1 , wherein generating the initial summary is performed prior to initiating the chatbot interaction.

3. The method of claim 1 , wherein the final summary of the chatbot interaction is a same summary as the updated summary.

4. The method of claim 1 , further comprising:

receiving second input from the first user during the chatbot interaction;

processing the second input with the natural language processing engine; and

wherein updating the initial summary based, at least in part, on the output of the processing by the natural language processing engine to generate the updated summary comprises updating the initial summary based on output of the processing of the first input and the second input by the natural language processing engine.

5. The method of claim 1 , further comprising:

processing the output of the natural language processing engine by a dialog manager to determine a next dialog interaction module; and

providing a request to the first user based on the determined next dialog interaction module.

6. The method of claim 5 , further comprising:

processing using the natural language processing engine, information from the next dialog interaction module to determine the request provided to the first user.

7. The method of claim 1 , wherein the updated summary includes a plurality of categories of information, and wherein updating the initial summary based, at least in part, on the output of the processing by the natural language processing engine comprises adding a new category of information to the initial summary.

8. The method of claim 1 , wherein the initial summary comprises a notification to the first user that the first user is eligible, based, at least in part, on an evaluation of stored information concerning the first user, for a service or transaction proposition.

9. The method of claim 1 , further comprising processing the output of the natural language processing engine by a dialog manager that uses slots and/or objects for identifying, grouping, and/or classifying information to acquire during the chatbot interaction and for determining whether additional input from the first user is necessary to complete a dialog module.

10. A computer system, comprising:

a communications interface configured to receive first input from a first user during a chatbot interaction and user data of the first user;

a natural language processing engine configured to process the first input; and

at least one computer hardware processor programmed to:

receive the user data of the first user via a network from at least one application executing on at least one computer;

generate an initial summary based, at least in part, on the received user data of the first user;

update the initial summary based, at least in part, on an output of the processing by the natural language processing engine to generate an updated summary, wherein the updating is performed prior to completion of the chatbot interaction; and

provide a final summary of the chatbot interaction, wherein the final summary of the chatbot interaction is based, at least in part, on the updated summary, to the at least one application executing on the at least one computer, the at least one application enabling, at least in part, a second user to follow up with the first user to schedule and/or complete, based, at least in part, on the final summary, a service or transaction mentioned during the chatbot interaction.

11. The computer system of claim 10 , wherein the at least one computer hardware processor is programmed to generate the initial summary prior to receiving the first input.

12. The computer system of claim 10 , wherein:

the communications interface is further configured to receive second input from the first user during the chatbot interaction,

the natural language processing engine is configured to process the second input, and

updating the initial summary based, at least in part, on the output of the processing by the natural language processing engine to generate the updated summary comprises updating the initial summary based on output of the processing of the first input and the second input by the natural language processing engine.

13. The computer system of claim 10 , further comprising:

a dialog manager configured to process the output of the natural language processing engine to determine a next dialog interaction module,

wherein the natural language processing engine is further configured to:

provide a request to the first user based on the determined next dialog interaction module; and

process information from the next dialog interaction module to determine the request provided to the first user.

14. The computer system of claim 10 , wherein the updated summary includes a plurality of categories of information, and wherein updating the initial summary based, at least in part, on the output of the processing by the natural language processing engine comprises adding a new category of information to the initial summary.

15. The computer system of claim 10 , wherein the initial summary comprises a notification to the first user that the first user is eligible, based, at least in part, on an evaluation of stored information concerning the first user, for a service or transaction proposition.

16. The computer system of claim 10 , wherein the communications interface is further configured to process the output of the natural language processing engine by a dialog manager that uses slots and/or objects for identifying, grouping, and/or classifying information to acquire during the chatbot interaction and for determining whether additional input from the first user is necessary to complete a dialog module.

17. At least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of summarizing a chatbot interaction with a first user, the method comprising:

using the at least one computer hardware processor to perform:

receiving user data of the first user via a network from at least one application executing on at least one computer;

generating an initial summary based, at least in part, on the user data of the first user;

receiving first input from the first user during the chatbot interaction;

processing the first input with a natural language processing engine;

updating the initial summary based, at least in part, on an output of the processing by the natural language processing engine to generate an updated summary, wherein the updating is performed prior to completion of the chatbot interaction; and

outputting a final summary of the chatbot interaction, wherein the final summary of the chatbot interaction is based, at least in part, on the updated summary, and wherein outputting the final summary of the chatbot interaction comprises providing the final summary of the chatbot interaction to the at least one application executing on the at least one computer hardware processor, the at least one application enabling, at least in part, a second user to follow up with the first user to schedule and/or complete, based, at least in part, on the final summary, a service or transaction mentioned during the chatbot interaction.

18. The at least one non-transitory computer-readable storage medium of claim 17 , wherein generating the initial summary is performed prior to initiating the chatbot interaction.

19. The at least one non-transitory computer-readable storage medium of claim 17 , wherein the method further comprises:

receiving second input from the first user during the chatbot interaction;

processing the second input with the natural language processing engine; and

wherein updating the initial summary based, at least in part, on the output of the processing by the natural language processing engine to generate the updated summary comprises updating the initial summary based on output of the processing of the first input and the second input by the natural language processing engine.

20. The at least one non-transitory computer-readable storage medium of claim 17 , wherein the method further comprises:

processing the output of the natural language processing engine by a dialog manager to determine a next dialog interaction module;

providing a request to the first user based on the determined next dialog interaction module; and

processing using the natural language processing engine, information from the next dialog interaction module to determine the request provided to the first user.

Assignments (2)
SECURITY INTEREST Recorded Aug 11, 2025
From: YSEOP SAS
To: CLARET EUROPEAN SPECIALTY LENDING COMPANY IV, S.A R.L.
Reel/Frame 071981/0024 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 19, 2020
From: DE MAZANCOURT, HUGUES SÉZILLE; KAESER, ALAIN
To: YSEOP SA
Reel/Frame 054484/0065 →
Continuity (1)
Provisional Application 63018889 · May 1, 2020
Cited By (12)
US 12,238,213 US 12,260,005 US 12,265,856 US 12,282,752 US 12,328,347 US 12,395,337 US 12,407,510 US 12,425,449 US 12,505,307 US 12,561,533 US 12,640,924 US 12,705,273