Generation of a chatbot

Patent metadata

Field	Value
Publication number	US-11552909-B2
Application number	US-202016920785-A
Country	US
Kind code	B2
Filing date	Jul 6, 2020
Priority date	Jul 6, 2020
Publication date	Jan 10, 2023
Grant date	Jan 10, 2023

Abstract

A computer-implemented method, computer system, and computer program product for for generation of a chatbot. The method may include receiving data in a first format. The method may include generating one or more clusters from the received data. The method may include labeling the generated one or more clusters. The method may include exporting the one or more labeled clusters into a cluster database. The method may include generating the chatbot using the one or more labeled clusters exported from the cluster database. The method may include executing a validation script into the chatbot to generate a report. The method may include receiving a determination on an accuracy of the chatbot based on the generated report. In response to determining that the chatbot is not accurate, the method may include determining whether a manual adjustment directly on the chatbot is needed.

First claim

What is claimed is:

1. A computer-implemented method for generation of a chatbot, the computer-implemented method comprising:
receiving data in a first format;
generating one or more clusters from the received data;
labeling the generated one or more clusters;
exporting the one or more labeled clusters into a cluster database;
generating the chatbot using the one or more labeled clusters exported from the cluster database;
executing a validation script that applies automated cross validation of the one or more labeled clusters into the chatbot to generate a report;
receiving a determination on an accuracy of the chatbot based on the generated report; and
in response to determining that the chatbot is not accurate, determining whether a manual adjustment directly on the chatbot is needed,
wherein the generated report contains information about quality and a suggested adjustment to the chatbot, the information about the quality including accuracy of responses and accuracy of the labeling of the generated one or more clusters.

2. The computer-implemented method of claim 1 , further comprising:
in response to determining that the chatbot is not accurate, receiving confirmation of the adjustment to the chatbot.

3. The computer-implemented method of claim 1 , further comprising:
in response to determining that the chatbot is accurate based upon a precision value in the generated report, determining that the chatbot is ready for use.

4. The computer-implemented method of claim 1 , wherein receiving the data in the first format further comprising:
separating the data from all data in a database; and converting the separated data into the first format.

5. The computer-implemented method of claim 1 , wherein the generated report containing the information about the quality includes a cluster distribution metric, a cluster confidence value, and a precision value.

6. The computer-implemented method of claim 1 , wherein the adjustment to the chatbot comprises:
relabeling the generated one or more clusters based upon suggestions provided in the generated report by a confusion matrix showing an expected classification of the one or more clusters.

7. The computer-implemented method of claim 1 , wherein the one or more labeled clusters exported from the cluster database is in the first format.

8. The computer-implemented method of claim 1 , wherein the cluster database contains all data separated into labeled clusters.

9. A computer system for generation of a chatbot, comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
receiving data in a first format;
generating one or more clusters from the received data;
labeling the generated one or more clusters;
exporting the one or more labeled clusters into a cluster database;
generating the chatbot using the one or more labeled clusters exported from the cluster database;
executing a validation script that applies automated cross validation of the one or more labeled clusters into the chatbot to generate a report;
receiving a determination on an accuracy of the chatbot based on the generated report; and
in response to determining that the chatbot is not accurate, determining whether a manual adjustment directly on the chatbot is needed,
wherein the generated report contains information about quality and a suggested adjustment to the chatbot, the information about the quality including accuracy of responses and accuracy of the labeling of the generated one or more clusters.

10. The computer system of claim 9 , further comprising:
in response to determining that the chatbot is not accurate, receiving confirmation of the adjustment to the chatbot.

11. The computer system of claim 9 , further comprising:
in response to determining that the chatbot is accurate based upon a precision value in the generated report, determining that the chatbot is ready for use.

12. The computer system of claim 9 , wherein receiving the data in the first format further comprising:
separating the data from all data in a database; and converting the separated data into the first format.

13. The computer system of claim 9 , wherein the generated report containing the information about the quality includes a cluster distribution metric, a cluster confidence value, and a precision value.

14. The computer system of claim 9 , wherein the adjustment to the chatbot comprises:
relabeling the generated one or more clusters based upon suggestions provided in the generated report by a confusion matrix showing an expected classification of the one or more clusters.

15. The computer system of claim 9 , wherein the one or more labeled clusters exported from the cluster database is in the first format.

16. The computer system of claim 9 , wherein the cluster database contains all data separated into labeled clusters.

17. A computer program product for generation of a chatbot, comprising:
one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more computer-readable tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:
receiving data in a first format;
generating one or more clusters from the received data;
labeling the generated one or more clusters;
exporting the one or more labeled clusters into a cluster database;
generating the chatbot using the one or more labeled clusters exported from the cluster database;
executing a validation script that applies automated cross validation of the one or more labeled clusters into the chatbot to generate a report;
receiving a determination on an accuracy of the chatbot based on the generated report; and
in response to determining that the chatbot is not accurate, determining whether a manual adjustment directly on the chatbot is needed,
wherein the generated report contains information about quality and a suggested adjustment to the chatbot, the information about the quality including accuracy of responses and accuracy of the labeling of the generated one or more clusters.

18. The computer program product of claim 17 , further comprising:
in response to determining that the chatbot is not accurate, receiving confirmation of the adjustment to the chatbot.

19. The computer program product of claim 17 , further comprising:
in response to determining that the chatbot is accurate based upon a precision value in the generated report, determining that the chatbot is ready for use.

20. The computer program product of claim 17 , wherein receiving the data in the first format further comprising:
separating the data from all data in a database; and
converting the separated data into the first format, the first format comprising a comma-values separated file.

Assignees

• Kyndryl Inc

Inventors

• Lopes De Moraes Marcelo
• Miranda Vieira Anthony
• Almeida Peterson
• Varga Sergio

Classifications

• G06F11/36

  Prevention of errors by analysis, debugging or testing of software · CPC title

• G06F11/3692

  for test results analysis · CPC title

• G06F40/242

  Dictionaries · CPC title

• G06F16/35

  Clustering; Classification · CPC title

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title