Systems and methods for identifying similar electronic content items

Patent metadata

Field	Value
Publication number	US-11544122-B2
Application number	US-202017137189-A
Country	US
Kind code	B2
Filing date	Dec 29, 2020
Priority date	Dec 29, 2020
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

Systems, methods and non-transitory computer readable media for detecting incidents are disclosed. The method includes receiving a primary issue creation event record for a primary issue, the event record including a description of the primary issue, and encoding the primary issue into a primary vector number based on the description of the primary issue. The method further includes identifying candidate issues and retrieving vector numbers of the identified candidate issues, computing distances between the primary vector number and each of the candidate vector numbers, and determining whether incident criteria is met based on the computed distances. In addition, the method includes determining that an incident has occurred upon determining that the incident criteria is met and generating an alert.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving a primary issue creation event record for a primary issue, the primary issue creation event record including a user-supplied description of the primary issue, the user-supplied description including user-supplied textual content;
encoding the primary issue into a primary vector number based at least in part on the user-supplied textual content;
identifying candidate issues and retrieving candidate vector numbers of the identified candidate issues;
computing distances between the primary vector number and each of the candidate vector numbers;
determining whether an incident criteria is met based on the computed distances; and
determining that an incident has occurred upon determining that the incident criteria is met and generating an alert.

2. The computer-implemented method of claim 1 , further comprising:
identifying one or more relevant users to communicate the alert to; and
communicating the alert to the identified relevant users.

3. The computer-implemented method of claim 2 , further comprising creating an incident dashboard, and communicating the alert to the identified relevant users comprises communicating a pointer to the incident dashboard.

4. The computer-implemented method of claim 1 , wherein the incident criteria is met if a threshold number of the candidate vector numbers are computed to be within a threshold distance of the primary vector number.

5. The computer-implemented method of claim 3 further comprising:
receiving a second issue creation event record for a second issue, the second issue creation event record including a second user-supplied description of the second issue, the second user-supplied description including second user-supplied textual content;
encoding the second issue into a second vector number based at least in part on the second user-supplied textual content;
computing a distance between the primary vector number and the second vector number;
determining whether the second issue is similar to the primary issue based on the computed distance; and
upon determining that the second issue is similar to the primary issue updating the incident dashboard to include information about the second issue.

6. The computer-implemented method of claim 1 , further comprising:
receiving a second issue creation event record for a second issue, the second issue creation event record including a second user-supplied description of the second issue, the second user-supplied description including second user-supplied textual content;
encoding the second issue into a second vector number based at least in part on the second user-supplied textual content;
computing a distance between the primary vector number and the second vector number;
determining whether the second issue is similar to the primary issue based on the computed distance;
upon determining that the second issue is not similar to the primary issue, assigning the second issue as the primary issue.

7. The method of claim 1 , wherein the primary vector number and the candidate vector numbers are generated using a word embedding model.

8. Non-transitory computer readable media storing instructions, which when executed by a processor cause the processor to perform a method, comprising:
receiving a primary issue creation event record for a primary issue, the primary issue creation event record including a user-supplied description of the primary issue, the user-supplied description including user-supplied textual content;
encoding the primary issue into a primary vector number based at least in part on the user-supplied textual content;
identifying candidate issues and retrieving candidate vector numbers of the identified candidate issues;
computing distances between the primary vector number and each of the candidate vector numbers;
determining whether an incident criteria is met based on the computed distances; and
determining that an incident has occurred upon determining that the incident criteria is met and generating an alert.

9. The non-transitory computer readable media of claim 8 , further comprising instructions which when performed by the processor cause the processor to:
identify one or more relevant users to communicate the alert to; and
communicate the alert to the identified relevant users.

10. The non-transitory computer readable media of claim 9 , further comprising instructions which when performed by the processor cause the processor to create an incident dashboard, and communicating the alert to the identified relevant users comprises communicating a pointer to the incident dashboard.

11. The non-transitory computer readable media of claim 8 , wherein the incident criteria is met if a threshold number of the candidate vector numbers are computed to be within a threshold distance of the primary vector number.

12. The non-transitory computer readable media of claim 10 , further comprising instructions which when performed by the processor cause the processor to:
receive a second issue creation event record for a second issue, the second issue creation event record including a second user-supplied description of the second issue the second user-supplied description including second user-supplied textual content;
encode the second issue into a second vector number based at least in part on the second user-supplied textual content;
compute a distance between the primary vector number and the second vector number;
determine whether the second issue is similar to the primary issue based on the computed distance;
upon determining that the second issue is similar to the primary issue, update the incident dashboard to include information about the second issue.

13. The non-transitory computer readable media of claim 8 , further comprising instructions, which when executed by the processor cause the processor to:
receive a second issue creation event record for a second issue, the second issue creation event record including a second user-supplied description of the second issue, the second user-supplied description including second user-supplied textual content;
encode the second issue into a second vector number based at least in part on the second user-supplied textual content;
compute a distance between the primary vector number and the second vector number;
determine whether the second issue is similar to the primary issue based on the computed distance;
upon determining that the second issue is not similar to the primary issue, assign the second issue as the primary issue.

14. The non-transitory computer readable media of claim 8 , wherein the primary vector number and the candidate vector numbers are generated using a word-embedding model.

15. A computer system comprising:
one or more processors;
memory in communication with the one or more processors, the memory comprising instructions to:
receive a primary issue creation event record for a primary issue, the primary issue creation event record including a user-supplied description of the primary issue, the user-supplied description including user-supplied textual content;
encode the primary issue into a primary vector number based at least in part on the user-supplied textual content;
identify candidate issues and retrieve candidate vector numbers of the identified candidate issues;
compute distances between the primary vector number and each of the candidate vector numbers;
determine whether an incident criteria is met based on the computed distances; and
determine that an incident has occurred upon determining that the incident criteria

Assignees

• Atlassian Pty Ltd
• Atlassian Inc
• Atlassian Us Inc

Inventors

• Awadhwal Gaurav
• Wondo Addo
• Sims Geoff
• Rho Gyeun Gyun
• Saad Ahmed
• Robilliard Simon Hugo

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06Q30/016 Primary

  After-sales · CPC title

• G06F9/542 Primary

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title