Method and system for generating and correcting classification models

Patent metadata

Field	Value
Publication number	US-11537820-B2
Application number	US-202016789811-A
Country	US
Kind code	B2
Filing date	Feb 13, 2020
Priority date	Aug 27, 2014
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

Data having some similarities and some dissimilarities may be clustered or grouped according to the similarities and dissimilarities. The data may be clustered using agglomerative clustering techniques. The clusters may be used as suggestions for generating groups where a user may demonstrate certain criteria for grouping. The system may learn from the criteria and extrapolate the groupings to readily sort data into appropriate groups. The system may be easily refined as the user gains an understanding of the data.

First claim

What is claimed is:

1. A non-transitory computer-readable storage media storing computer-readable instructions that, when executed by a processor of a system, cause the system to:
generate a first classification model based on a first indication that a first portion of a first data set is associated with a first bucket and a second classification model based on a second indication that the first portion of the first data set is associated with a second bucket using data comprising structured data, unstructured data, and partially structured data;
compare, using a comparator, (1) a first score using test results from the first classification model based on a data set of natural language inputs from conversations of calls or chats and (2) a second score using test results from the second classification model based on the data set of natural language inputs from the conversations of calls or chats;
when the first score agrees with the second score within a threshold range, validate the first classification model;
when the first score is different from the second score with respect to the threshold range, display, on a display of a user device, a clarification question for a user;
when an indication is received from the user, in response to the clarification question, that the first classification model is correct, update the second classification model based on the indication; and
when an indication is received from the user, in response to the clarification question, that the second classification model is correct, update the first classification model based on the indication.

2. The non-transitory computer-readable storage media of claim 1 , wherein the first classification model comprises a symbolic language model; and the second classification model comprises a statistical language model.

3. The non-transitory computer-readable storage media of claim 1 , wherein the clarification question comprises a question asking the user to select an appropriate answer to an input statement.

4. The non-transitory computer-readable storage media of claim 1 , wherein the data set comprises disparate types of data.

5. The non-transitory computer-readable storage media of claim 1 , wherein the data set comprises imported data.

6. The non-transitory computer-readable storage media of claim 1 , wherein the data set comprises markup language data.

7. A non-transitory computer-readable storage media storing computer-readable instructions that, when executed by a processor of a system, cause the system to:
generate a first classification model based on a first indication that a first portion of a first data set is associated with a first bucket and a second classification model based on a second indication that the first portion of the first data set is associated with a second bucket using data comprising structured data, unstructured data, and partially structured data;
compare, by a comparator, (1) a first score using test results from the first classification model based on a data set of natural language inputs from conversations of calls or chats and (2) a second score using test results from the second classification model based on the data set of natural language inputs from the conversations of calls or chats;
when the first score agrees with the second score within a threshold range, validate the first classification model;
when the first score is different from the second score within a first threshold difference, display, on a display of a user device, a first clarification question for a user, and update the first classification model based on an answer to the first clarification question; and
when the first score is different from the second score within a second threshold difference and outside of the first threshold difference, display on a display of the user device, a second clarification question for the user, and update the first classification model based on an answer to the second clarification question.

8. The non-transitory computer-readable storage media of claim 7 , wherein the first classification model comprises a symbolic language model; and the second classification model comprises a statistical language model.

9. The non-transitory computer-readable storage media of claim 7 , wherein the first clarification question comprises a question asking the user to select an appropriate answer to an input statement.

10. The non-transitory computer-readable storage media of claim 7 , wherein the second clarification question comprises a question asking the user to select an appropriate restatement of an input statement, the appropriate restatement of the input being a leading restatement of the input statement.

11. The non-transitory computer-readable storage media of claim 7 , wherein the data set comprises disparate types of data.

12. The non-transitory computer-readable storage media of claim 7 , wherein the data set comprises imported data.

13. The non-transitory computer-readable storage media of claim 7 , wherein the data set comprises markup language data.

14. A system comprising:
one or more processors; and
a memory communicably coupled to the one or more processors and storing instructions that when executed by the one or more processors cause the system to:
generate a first classification model based on a first indication that a first portion of a first data set is associated with a first bucket and a second classification model based on a second indication that the first portion of the first data set is associated with a second bucket using data comprising structured data, unstructured data, and partially structured data;
compare, using a comparator, (1) a first score using test results from the first classification model based on a data set of natural language inputs from conversations of calls or chats and (2) a second score using test results from the second classification model based on the data set of natural language inputs from the conversations of calls or chats;
when the first score agrees with the second score within a threshold range, validate, by the one or more processors, the first classification model;
when the first score is different from the second score with respect to the threshold range, display, on a display of a user device, a clarification question for a user;
when an indication is received from the user, in response to the clarification question, that the first classification model is correct, update the second classification model based on the indication; and
when an indication is received from the user, in response to the clarification question, that the second classification model is correct, update the first classification model based on the indication.

15. The system of claim 14 , wherein the first classification model comprises a symbolic language model; and the second classification model comprises a statistical language model.

16. The system of claim 14 , wherein the clarification question comprises a question asking the user to select an appropriate answer to an input statement.

17. A system comprising:
one or more processors; and
a memory communicably coupled to the one or more processors and storing instructions that when executed by the one or more processors cause the system to:
generate a first classification model based on a first indication that a first portion of a first data set is associated with a first bucket and a second classification model based on a second indication that the first portion of the first data set is associated with a second bucket using data comprising structured data, unstructured data, an

Assignees

• Verint Americas Inc

Inventors

• Brown Fred A
• Miller Tanya M
• Wooters Charles C
• Brown Megan
• Brown Molly Q

Classifications

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06F16/358 Primary

  Browsing; Visualisation therefor · CPC title

• G06F18/41

  Interactive pattern learning with a human teacher · CPC title

• G06K9/6263 Primary

  Physics · mapped topic

• G06K9/6254

  Physics · mapped topic