IP Library Granted Patent US 10,923,115
Granted Patent B2
US 10,923,115 · App. 16/590,964 · Granted Feb 16, 2021

Dynamically generated dialog

Inventors: Edgar Adolfo Zamora Duran (Heredia, CR); Franz Friedrich Liebinger Portela (Heredia, CR); Yanil Zeledon (Heredia, CR); Roxana Monge Nunez (Perez Zeledon, CR)
Assignee: International Business Machines Corporation
G10L15/1815G06F40/242G06F40/30G06N3/08G10L15/22G10L15/24G10L15/30G06F40/58G10L15/26G10L2015/223
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 10,923,115
App. No.
16/590,964
Granted
Feb 16, 2021
Kind
B2
Abstract

A method and system of dynamically generating computerized dialog. Natural language input previously from a user and cognitive context are analyzed. A dictionary is selected as a function of the natural language input and stored information previously known about the user. A corpus including knowledge of the topics of interest is further selected. One or more expressions are extracted from a network accessible data source. The one or more expressions extracted from the network accessible data source are filtered through the dictionary and the corpus. Dialog is generated in response to the natural language input, as a function of the cognitive context and topic of interest by integrating the one or more expressions filtered through the dictionary and corpus.

Claims (43)

1. A method for dynamically generating computerized dialog, said method comprising:

analyzing, by one or more processors of a computer system, both natural language input previously from a user and cognitive context;

selecting, by the one or more processors, a dictionary as a function of the natural language input and stored information previously known about the user;

further selecting, by the one or more processors, a corpus comprising knowledge of the topics of interest;

extracting, by the one or more processors, one or more expressions from a network accessible data source;

filtering, by the one or more processors, the one or more expressions extracted from the network accessible data source through the dictionary and the corpus; and

generating, by the one or more processors, dialog in response to the natural language input, as a function of the cognitive context and topic of interest by integrating the one or more expressions filtered through the dictionary and corpus.

2. The method of claim 1 , wherein the natural language input is selected from the group consisting of audio and video input, recorded by a recording system comprising a camera and a microphone.

3. The method of claim 2 , wherein the cognitive context comprises body language and emotion recorded by the recording system during the natural language input.

4. The method of claim 3 , wherein the cognitive context indicates one or more topics of interest to avoid during the analyzing step.

5. The method of claim 1 , wherein said filtering comprises:

translating, by the one or more processors, the one or more expressions from a native language to a language of the dictionary.

6. The method of claim 1 , wherein said extracting targets extraction of expressions from the network accessible data source created by data source users having at least one parameter in common with the stored information previously known about the user.

7. The method of claim 1 , wherein the network accessible data source is a social media website.

8. The method of claim 1 , said method further comprising:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in a computer system, where the computer-readable program code in combination with the computer system is configured to implement said analyzing, said selecting, said further selecting, said extracting, said filtering and said generating.

9. A computer system, comprising: one or more processors, one or more memory devices coupled to the one or more processors, and one or more computer readable storage device coupled to the one or more processors, wherein the one or more storage devices contains program code executable by the one or more processors via the one or more memory devices to implement a method for dynamically generating computerized dialog, said method comprising:

analyzing, by the one or more processors, both natural language input previously from a user and cognitive context;

selecting, by the one or more processors, a dictionary as a function of the natural language input and the stored information previously known about the user;

further selecting, by the one or more processors, a corpus comprising knowledge of the topics of interest;

extracting, by the one or more processors, one or more expressions from a network accessible data source;

filtering, by the one or more processors, the one or more expressions extracted from the network accessible data source through the dictionary and the corpus; and

generating, by the one or more processors, dialog in response to the natural language input, as a function of the cognitive context and topic of interest by integrating the one or more expressions filtered through the dictionary and corpus.

10. The computer system of claim 9 , wherein the computer system further comprises:

a recording system including a camera and a microphone, wherein the natural language input is selected from the group consisting of audio and video input, recorded by the recording system.

11. The computer system of claim 10 , wherein the cognitive context comprises body language and emotion recorded by the recording system during the natural language input.

12. The computer system of claim 11 , wherein the cognitive context indicates one or more topics of interests to avoid during the analyzing step.

13. The computer system of claim 9 , wherein said filtering comprises:

translating, by the one or more processors, the one or more expressions from a native language to a language of the dictionary.

14. The computer system of claim 9 , wherein said extracting targets extraction of expressions from the network accessible data source created by data source users having at least one parameter in common with the stored information previously known about the user.

15. A computer program product comprising: one or more computer readable hardware storage devices having computer readable program code stored therein, said program code containing instructions executable by one or more processors of a computer system to implement a method for dynamically generating computerized dialog, said method comprising:

analyzing, by the one or more processors, both natural language input previously from a user and cognitive context;

selecting, by the one or more processors, a dictionary as a function of the natural language input and the stored information previously known about the user;

further selecting, by the one or more processors, a corpus comprising knowledge of the topics of interest;

extracting, by the one or more processors, one or more expressions from a network accessible data source;

filtering, by the one or more processors, the one or more expressions extracted from the network accessible data source through the dictionary and the corpus; and

generating, by the one or more processors, dialog in response to the natural language input, as a function of the cognitive context and topic of interest by integrating the one or more expressions filtered through the dictionary and corpus.

16. The computer program product of claim 15 , wherein the natural language input is selected from the group consisting of audio and video input, recorded by a recording system comprising a camera and a microphone.

17. The computer program product of claim 16 , wherein the cognitive context comprises body language and emotion recorded by the recording system during the natural language input.

18. The computer program product of claim 17 , wherein the cognitive context indicates one or more topics of interest to avoid during the analyzing step.

19. The computer program product of claim 15 , wherein said filtering comprises:

translating, by the processor, the one or more expressions from a native language to a language of the dictionary.

20. The computer program product of claim 15 , wherein said extracting targets extraction of expressions from the network accessible data source created by data source users having at least one parameter in common with the stored information previously known about the user.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 15, 2021
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: AIRBNB, INC.
Reel/Frame 056427/0193 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 2, 2019
From: ZAMORA DURAN, EDGAR ADOLFO; LIEBINGER PORTELA, FRANZ FRIEDRICH; ZELEDON, YANIL; MONGE NUNEZ, ROXANA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 050604/0462 →