IP Library › Granted Patent US 12,266,037
Granted Patent B2
US 12,266,037 · App. 17/943,023 · Granted Apr 1, 2025

Systems and methods for visualizing problem areas of an automated question answering system

Inventors: Charles Wooters (Livermore, CA); Yochai Konig (San Francisco, CA); Christos Melidis (Central Macedonia, GR); Arnon Mazza (Givatayim, IL); George Seif (Toronto, CA); Chen Qian (Kitchener, CA); Ives José de Albuquerque Macêdo, Jr. (North Vancouver, CA); Jérôme Solis (Montreal, CA)
Assignee: ADA SUPPORT INC.
G06T11/206G06F40/30G06F40/35G10L15/1822G10L15/183
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 12,266,037
App. No.
17/943,023
Granted
Apr 1, 2025
Kind
B2
Abstract

Systems and method for visualizing data for an automated question answering system are disclosed. The method includes identifying a first answer associated with a first query; identifying a second answer associated with a second query; determining a criterion of the first answer with respect to the second answer; and visually representing the first answer and the second answer based on the criterion.

Claims (38)

1. A method for visualizing data for an automated question answering system, the method comprising:

identifying a first answer associated with a first query;

identifying a second answer associated with a second query;

determining a semantic relationship between the first query and the second query;

determining a criterion of the first answer with respect to the second answer, wherein the determining the criterion includes determining that the semantic relationship between the first query and the second query is greater than a semantic relationship between the first query and another query associated with the first answer; and

visually representing the first answer and the second answer based on the criterion.

2. The method of claim 1 , wherein the criterion is indicative of the first answer being confused with the second answer.

3. The method of claim 2 , wherein the visually representing the first answer and the second answer includes displaying, in a network graph, a first node for the first answer, a second node for a second answer, and a directed edge connecting the first node and the second node, wherein a direction of the directed edge is indicative of a direction of confusion resulting from the first answer being confused with the second answer.

4. The method of claim 2 , wherein in response to determining the criterion, recommending an action for addressing confusion resulting from the first answer being confused with the second answer.

5. The method of claim 1 , wherein the first query and the second query are for training the automated question answering system.

6. The method of claim 1 further comprising:

identifying a third query;

determining that the third query is unassigned to an answer; and

visually representing the third query based on the determining.

7. The method of claim 1 further comprising:

identifying a third answer;

determining a number of queries associated with the third answer; and

visually representing the third answer based on the determining.

8. A system for visualizing data comprising:

a processor; and

a memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to:

identify a first answer associated with a first query;

identify a second answer associated with a second query;

determine a semantic relationship between the first query and the second query;

determine a criterion of the first answer with respect to the second answer, wherein the instructions that cause the processor to determine the criterion include instructions that cause the processor to determine that the semantic relationship between the first query and the second query is greater than a semantic relationship between the first query and another query associated with the first answer; and

visually represent the first answer and the second answer based on the criterion.

9. The system of claim 8 , wherein the criterion is indicative of the first answer being confused with the second answer.

10. The system of claim 9 , wherein the instructions that cause the processor to visually represent the first answer and the second answer include instructions that cause the processor to display, in a network graph, a first node for the first answer, a second node for a second answer, and a directed edge connecting the first node and the second node, wherein a direction of the directed edge is indicative of a direction of confusion resulting from the first answer being confused with the second answer.

11. The system of claim 9 , wherein the instructions further cause the processor to, in response to determining the criterion, recommend an action for addressing confusion resulting from the first answer being confused with the second answer.

12. The system of claim 8 , wherein the first query and the second query are for training an automated question answering system.

13. The system of claim 8 , wherein the instructions further cause the processor to:

identify a third query;

determine that the third query is unassigned to an answer; and

visually represent the third query based on the determining.

14. The system of claim 8 , wherein the instructions further cause the processor to:

identify a third answer;

determine a number of queries associated with the third answer; and

visually represent the third answer based on the determining.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 12, 2022
From: WOOTERS, CHARLES; KONIG, YOCHAI; MELIDIS, CHRISTOS; MAZZA, ARNON; SEIF, GEORGE; QIAN, CHEN; MACÊDO, IVES JOSÉ DE ALBUQUERQUE, JR.; SOLIS, JÉRÔME
To: ADA SUPPORT INC.
Reel/Frame 061419/0515 →
Continuity (1)
Related Publication 20240087187A1 · Mar 14, 2024
References Cited (4)
US 11394667B2 · Bobbarjung · 2022 [cited by examiner]
US 11734579B2 · Neelamana · 2023 [cited by examiner]
US 12002455B2 · Sridhar · 2024 [cited by examiner]
U.S. Appl. No. 17/889,186, filed Aug. 16, 2022, entitled “Systems and Methods for Generating a Chatbot”. [cited by applicant]