IP Library › Granted Patent US 11,552,966
Granted Patent B2
US 11,552,966 · App. 17/032,006 · Granted Jan 10, 2023

Generating and mutually maturing a knowledge corpus

Inventors: Shikhar Kwatra (Raleigh, NC); Adam Lee Griffin (Dubuque, IA); Indervir Singh Banipal (Austin, TX); Sarbajit K. Rakshit (Kolkata, IN); Laura Grace Ellis (Austin, TX)
Assignee: International Business Machines Corporation
H04L63/1416G06F3/167G06F16/248G06N5/04G06N20/00
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 11,552,966
App. No.
17/032,006
Granted
Jan 10, 2023
Kind
B2
Abstract

In an approach to mature a knowledge corpus using artificial intelligence (AI) and user collaboration, embodiments create, by an AI response system, a knowledge corpus based on retrieved data associated with a first user. Additionally, embodiments execute, by the AI response system, a search to locate one or more matching knowledge corpora based on a request of the first user, and identify, by an anonymous network, at least one cluster of one or more anonymous second users having respective search requests that substantially match the search request of the first user. Furthermore, embodiments execute an AI exchange between the identified one or more anonymous second users and the first user, and mature the knowledge corpus, via the AI response system, based on the AI exchange between the first user and the identified one or more anonymous second users.

Claims (68)

1. A computer-implemented method for maturing a knowledge corpus using artificial intelligence (AI) and user collaboration, the method comprising:

creating, by an AI response system, a knowledge corpus based on retrieved data associated with a first user;

executing, by the AI response system, a search to locate one or more matching knowledge corpora based on a request of the first user;

identifying, by an anonymous network, at least one cluster of one or more anonymous second users having respective search requests that substantially match the search request of the first user;

executing an AI exchange between the identified one or more anonymous second users and the first user; and

maturing the knowledge corpus, via the AI response system, based on the AI exchange between the first user and the identified one or more anonymous second users.

2. The method of claim 1 , further comprising:

receiving, by a user interface or microphone, user dialog or user text data input; and

receiving real-time user interaction data, wherein receiving the real-time user interaction data comprises: receiving user dialog from a microphone, or a transcript or text data of a dialog of a user from at least one of: a deep learning framework, a natural language processor (NLP), a natural-language understanding (NLU) neural network, and one or more cognitive toolkits.

3. The method of claim 1 , further comprising:

responsive to having difficulty registering a voice command or request of the first user, displaying, by a user interface, or providing an auditory notification by a speaker, a responsive notification to the first user that prompts the first user to clarify the voice command or request of the first user, wherein the responsive notification identifies the voice command or request of the first user and enables the first user to correct the voice command in the responsive notification through the user interface, or a microphone via voice dictation.

4. The method of claim 1 , further comprising:

determining a selected trading party is secure, wherein the determining the selected trading party is secure comprises:

displaying, by a smart query engine, a safety rating of one or more interested trading parties to the first user to alert the first user of a potential security threat.

5. The method of claim 1 , further comprising:

alerting the first user of a potential security threat by calculating a safety rating score based on respective safety ratings of one or more interested parties; and

issuing one or more notifications to the first user when the first user selects a trading party that has a calculated safety rating score below a predetermined threshold.

6. The method of claim 1 , further comprising:

enabling the first user to selectively manage one or more knowledge corpora, wherein the first user can select to enable access to at least a portion of the knowledge corpus of the one or more knowledge corpora for AI exchange through the anonymous network.

7. The method of claim 1 , further comprising:

retrieving historical user data of the first user from a database; and

creating a user account for the first user based on the retrieved historical user data and interactions of the first user with the AI response system.

8. A computer system for maturing a knowledge corpus using artificial intelligence (AI) and user collaboration, the computer system comprising:

one or more computer processors;

one or more computer readable storage devices;

program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:

program instructions to create, by an AI response system, a knowledge corpus based on retrieved data associated with a first user;

program instructions to execute, by the AI response system, a search to locate one or more matching knowledge corpora based on a request of the first user;

program instructions to identify, by an anonymous network, at least one cluster of one or more anonymous second users having respective search requests that substantially match the search request of the first user;

program instructions to execute an AI exchange between the identified one or more anonymous second users and the first user; and

program instructions to mature the knowledge corpus, via the AI response system, based on the AI exchange between the first user and the identified one or more anonymous second users.

9. The computer system of claim 8 , further comprising:

program instructions to receive, by a user interface or microphone, user dialog or user text data input; and

program instructions to receive real-time user interaction data, wherein receiving the real-time user interaction data comprises: receiving user dialog from a microphone, or a transcript or text data of a dialog of a user from at least one of: a deep learning framework, a natural language processor (NLP), a natural-language understanding (NLU) neural network, and one or more cognitive toolkits.

10. The computer system of claim 8 , further comprising:

responsive to having difficulty registering a voice command or request of the first user, program instructions to display, by a user interface, or providing an auditory notification by a speaker, a responsive notification to the first user that prompts the first user to clarify the voice command or request of the first user, wherein the responsive notification identifies the voice command or request of the first user and enables the first user to correct the voice command in the responsive notification through the user interface, or a microphone via voice dictation.

11. The computer system of claim 8 , further comprising:

program instructions to determine a selected trading party is secure, wherein the determining the selected trading party is secure comprises:

program instructions to display, by a smart query engine, a safety rating of one or more interested trading parties to the first user to alert the first user of a potential security threat.

12. The computer system of claim 8 , further comprising:

program instructions to alert the first user of a potential security threat by calculating a safety rating score based on respective safety ratings of one or more interested parties; and

program instructions to issue one or more notifications to the first user when the first user selects a trading party that has a calculated safety rating score below a predetermined threshold.

13. The computer system of claim 8 , further comprising:

program instructions to enable the first user to selectively manage one or more knowledge corpora, wherein the first user can select to enable access to at least a portion of the knowledge corpus of the one or more knowledge corpora for AI exchange through the anonymous network.

14. The computer system of claim 8 , further comprising:

program instructions to retrieve historical user data of the first user from a database; and

program instructions to create a user account for the first user based on the retrieved historical user data and interactions of the first user with the AI response system.

15. A computer program product for extracting test datasets for testing and resource optimization, the computer program product comprising:

one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:

program instructions to create, by an AI response system, a knowledge corpus based on retrieved data associated with a first user;

program instructions to execute, by the AI response system, a search to locate one or more matching knowledge corpora based on a request of the first user;

program instructions to identify, by an anonymous network, at least one cluster of one or more anonymous second users having respective search requests that substantially match the search request of the first user;

program instructions to execute an AI exchange between the identified one or more anonymous second users and the first user; and

program instructions to mature the knowledge corpus, via the AI response system, based on the AI exchange between the first user and the identified one or more anonymous second users.

16. The computer program product of claim 15 , further comprising:

program instructions to receive, by a user interface or microphone, user dialog or user text data input; and

program instructions to receive real-time user interaction data, wherein receiving the real-time user interaction data comprises: receiving user dialog from a microphone, or a transcript or text data of a dialog of a user from at least one of: a deep learning framework, a natural language processor (NLP), a natural-language understanding (NLU) neural network, and one or more cognitive toolkits.

17. The computer program product of claim 15 , further comprising:

responsive to having difficulty registering a voice command or request of the first user, program instructions to display, by a user interface, or providing an auditory notification by a speaker, a responsive notification to the first user that prompts the first user to clarify the voice command or request of the first user, wherein the responsive notification identifies the voice command or request of the first user and enables the first user to correct the voice command in the responsive notification through the user interface, or a microphone via voice dictation.

18. The computer program product of claim 15 , further comprising:

program instructions to determine a selected trading party is secure, wherein the determining the selected trading party is secure comprises:

program instructions to display, by a smart query engine, a safety rating of one or more interested trading parties to the first user to alert the first user of a potential security threat.

19. The computer program product of claim 15 , further comprising:

program instructions to alert the first user of a potential security threat by calculating a safety rating score based on respective safety ratings of one or more interested parties; and

program instructions to issue one or more notifications to the first user when the first user selects a trading party that has a calculated safety rating score below a predetermined threshold.

20. The computer program product of claim 15 , further comprising:

program instructions to retrieve historical user data of the first user from a database; and

program instructions to create a user account for the first user based on the retrieved historical user data and interactions of the first user with the AI response system; and program instructions to enable the first user to selectively manage one or more knowledge corpora, wherein the first user can select to enable access to at least a portion of the knowledge corpus of the one or more knowledge corpora for AI exchange through the anonymous network.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2020
From: KWATRA, SHIKHAR; GRIFFIN, ADAM LEE; BANIPAL, INDERVIR SINGH; RAKSHIT, SARBAJIT K.; ELLIS, LAURA GRACE
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 053880/0677 →
Continuity (1)
Related Publication 20220103574A1 · Mar 31, 2022