Discovering insights and/or resolutions from collaborative conversations

Patent metadata

Field	Value
Publication number	US-11409593-B1
Application number	US-202117394667-A
Country	US
Kind code	B1
Filing date	Aug 5, 2021
Priority date	Aug 5, 2021
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

Methods, computer program products, and/or systems are provided that perform the following operations: in an information technology (IT) management system, grouping one or more ongoing service failure events into a service failure record; identifying a representative event for the service failure record; identifying one or more conversations that relate to the one or more ongoing service events; computing, using a similarity algorithm, feature similarity scores for respective conversations of the one or more conversations based, at least in part, on the features associated with the representative event and features associated with the respective conversations; linking a subset of the one or more conversations to the one or more ongoing service events in the service failure record based, at least in part, on the computed feature similarity scores; and providing the service failure record to a collaboration platform utilized in addressing the one or more ongoing service events.

First claim

What is claimed is:

1. A computer-implemented method comprising:
in an information technology (IT) management system, grouping one or more ongoing service failure events into a service failure record;
identifying a representative event for the service failure record from the one or more ongoing service failure events grouped in the service failure record;
extracting features associated with the representative event;
identifying one or more conversations, stored in the IT management system, that relate to the one or more ongoing service events;
computing, using a similarity algorithm, feature similarity scores for respective conversations of the one or more conversations based, at least in part, on the extracted features associated with the representative event and features associated with the respective conversations;
linking a subset of the one or more conversations to the one or more ongoing service events in the service failure record based, at least in part, on the computed feature similarity scores; and
providing the service failure record to a collaboration platform utilized in addressing the one or more ongoing service events.

2. The computer-implemented method of claim 1 , further comprising:
obtaining feedback on the service failure record from one or more users of the collaboration platform; and
training one or more components of the similarity algorithm based, at least in part, on the obtained feedback.

3. The computer-implemented method of claim 2 , wherein training one or more components of the similarity algorithm based, at least in part, on the obtained feedback comprises training a machine learning algorithm to generate feature weights utilized in the similarity algorithm.

4. The computer-implemented method of claim 3 , wherein the training of the machine learning algorithm utilizes a learning to rank method.

5. The computer-implemented method of claim 3 , wherein the feature weights include: (i) a first feature weight corresponding to a region feature of the representative event, (ii) a second feature weight corresponding to a log template feature of the representative event, (iii) a third feature weight corresponding to an entity feature of the representative event, and (iv) a fourth feature weight corresponding to a change ticket feature of the representative event.

6. The computer-implemented method of claim 1 , wherein identifying one or more conversations, stored in the IT management system, that relate to the one or more ongoing service events comprises:
identifying one or more new conversations, stored in the IT management system, that are responsive to the one or more ongoing service events; and
identifying one or more historical conversations, stored in the IT management system, based, at least in part, on the one or more new conversations.

7. The computer-implemented method of claim 1 , further comprising:
identifying, in the IT management system, one or more change tickets associated with the one or more ongoing service events based, at least in part, on system topology objects associated with the ongoing service events; and
linking the one or more change tickets to the one or more ongoing service events in the service failure record.

8. A computer program product comprising a computer readable storage medium having stored thereon:
program instructions to, in an information technology (IT) management system, group one or more ongoing service failure events into a service failure record;
program instructions to identify a representative event for the service failure record from the one or more ongoing service failure events grouped in the service failure record;
program instructions to extract features associated with the representative event;
program instructions to identify one or more conversations, stored in the IT management system, that relate to the one or more ongoing service events;
program instructions to compute, using a similarity algorithm, feature similarity scores for respective conversations of the one or more conversations based, at least in part, on the extracted features associated with the representative event and features associated with the respective conversations;
program instructions to link a subset of the one or more conversations to the one or more ongoing service events in the service failure record based, at least in part, on the computed feature similarity scores; and
program instructions to provide the service failure record to a collaboration platform utilized in addressing the one or more ongoing service events.

9. The computer program product of claim 8 , the computer readable storage medium having further stored thereon:
program instructions to obtain feedback on the service failure record from one or more users of the collaboration platform; and
program instructions to train one or more components of the similarity algorithm based, at least in part, on the obtained feedback.

10. The computer program product of claim 9 , wherein the program instructions to train one or more components of the similarity algorithm based, at least in part, on the obtained feedback comprise program instructions to train a machine learning algorithm to generate feature weights utilized in the similarity algorithm.

11. The computer program product of claim 10 , wherein the training of the machine learning algorithm utilizes a learning to rank method.

12. The computer program product of claim 10 , wherein the feature weights include: (i) a first feature weight corresponding to a region feature of the representative event, (ii) a second feature weight corresponding to a log template feature of the representative event, (iii) a third feature weight corresponding to an entity feature of the representative event, and (iv) a fourth feature weight corresponding to a change ticket feature of the representative event.

13. The computer program product of claim 8 , wherein the program instructions to identify one or more conversations, stored in the IT management system, that relate to the one or more ongoing service events comprise:
program instructions to identify one or more new conversations, stored in the IT management system, that are responsive to the one or more ongoing service events; and
program instructions to identify one or more historical conversations, stored in the IT management system, based, at least in part, on the one or more new conversations.

14. The computer program product of claim 8 , the computer readable storage medium having further stored thereon:
program instructions to identify, in the IT management system, one or more change tickets associated with the one or more ongoing service events based, at least in part, on system topology objects associated with the ongoing service events; and
program instructions to link the one or more change tickets to the one or more ongoing service events in the service failure record.

15. A computer system comprising:
a processor set; and
a computer readable storage medium;
wherein:
the processor set is structured, located, connected and programmed to run program instructions stored on the computer readable storage medium; and
the stored program instructions include:
program instructions to, in an information technology (IT) management system, group one or more ongoing service failure events into a service failure record;
program instructions to identify a representative event for the service failure record from the one or more ongoing service failure events grouped in the service failure record;
program instructions to extract features associated with the representative event;
progra

Assignees

• IBM

Inventors

• Kumar Harshit
• Batta Raghav
• Hwang Jinho
• Shwartz Larisa
• Dasgupta Gargi B
• Mohapatra Prateeti
• Azad Amar Prakash
• Verma Nikhil
• Gupta Ajay
• Aggarwal Pooja
• Krchák Jakub

Classifications

• G06F11/0793

  Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40) · CPC title

• G06F11/079 Primary

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/0781 Primary

  Error filtering or prioritizing based on a policy defined by the user or on a policy defined by a hardware/software module, e.g. according to a severity level · CPC title

• G06F11/0709

  in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems · CPC title