Identifying clusters for service management operations

Patent metadata

Field	Value
Publication number	US-11062324-B2
Application number	US-201916513150-A
Country	US
Kind code	B2
Filing date	Jul 16, 2019
Priority date	May 5, 2017
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

Client instance data including a plurality of incidents is obtained, each incident including a plurality of fields. A target field and an evaluation field are selected from among the plural fields. The plurality of incidents are grouped into a plurality of clusters based on a degree of a natural language text similarity of respective target fields in the plurality of incidents. A quality value is determined for each of the plurality of clusters based on the degree of the natural language text similarity of respective target fields in grouped incidents of the cluster from among the plurality of incidents, and based on respective evaluation fields. Each of the plurality of clusters is ranked based on the respective quality value of the cluster and a number of the grouped incidents of the cluster. At least one of the ranked plurality of clusters is identified to perform a service management operation.

First claim

What is claimed is:

1. A system, comprising:
a processor; and
a memory, accessible by the processor, the memory storing instructions, that when executed by the processor, cause the processor to:
receive, via a graphical user interface, one or more inputs associated with a data source;
extract historical incident report data for a plurality of incidents from the data source, wherein the historical incident report data comprises one or more text-based fields completed in natural language associated with each incident of the plurality of incidents and one or more value-based evaluation fields associated with each incident of the plurality of incidents;
group the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity between one or more text-based fields associated with each incident of the plurality of incidents and an additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
determine a respective evaluation value associated with each cluster of the plurality of clusters based on the additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
rank the plurality of clusters based at least on respective numbers of incidents in each cluster of the plurality of clusters and the respective evaluation value associated with each cluster;
identify one or more respective issues in common between each incident of each cluster based on the one or more text-based fields;
identify one or more service management operations associated with resolution of the one or more respective issues; and
provide, via the graphical user interface, a recommendation to implement the one or more service management operations to resolve a new incident.

2. The system of claim 1 , wherein the one or more service management operations comprises implementation of a virtual agent configured to assist a user in resolving the new incident.

3. The system of claim 2 , wherein the virtual agent is configured to utilize conversation trees based on the one or more respective issues and the one or more service management operations to assist the user in resolving the new incident.

4. The system of claim 1 , wherein the one or more service management operations comprises an implementation of a workflow based on a ranked cluster of the plurality of clusters to automatically resolve the new incident.

5. The system of claim 1 , wherein the one or more service management operations comprises a display of a knowledge product to assist a user in resolving the new incident.

6. The system of claim 1 , wherein the instructions cause the processor to:
perform the one or more service management operations to resolve the plurality of incidents associated with a ranked cluster of the plurality of clusters based on the one or more identified respective issues.

7. A method, comprising:
receiving, via a graphical user interface, one or more inputs associated with a data source;
extracting historical incident report data for a plurality of incidents from the data source, wherein the historical incident report data comprises one or more text-based fields completed in natural language associated with each incident of the plurality of incidents and one or more value-based evaluation fields associated with each incident of the plurality of incidents;
grouping the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity between one or more text-based fields associated with each incident of the plurality of incidents and an additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
determining a respective evaluation value associated with each cluster of the plurality of clusters based on the additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
ranking the plurality of clusters based at least on respective numbers of incidents in each cluster of the plurality of clusters and the respective evaluation value associated with each cluster;
identifying one or more respective issues in common between each incident of each cluster based on the one or more text-based fields;
identifying one or more service management operations associated with resolution of the one or more respective issues; and
providing, via the graphical user interface, a recommendation to implement the one or more service management operations to resolve a new incident, wherein the one or more service management operations comprise an implementation of a virtual agent configured to assist a user in resolving the new incident, an implementation of a workflow based on a particular cluster to automatically resolve the new incident, or a display of a knowledge product to assist a user in resolving the new incident, or a combination thereof.

8. The method of claim 7 , wherein the virtual agent is configured to utilize conversation trees based on the one or more respective issues and the one or more service management operations to assist the user in resolving the new incident.

9. The method of claim 7 , comprising:
performing the one or more service management operations to resolve the plurality of incidents associated with a ranked cluster of the plurality of clusters based on the one or more identified respective issues.

10. The method of claim 7 , wherein the one or more inputs comprise a target text-based field of the one or more text-based fields, and wherein grouping the plurality of incidents into the plurality of clusters is based on the target text-based field associated with each incident of the plurality of incidents.

11. The method of claim 7 , wherein the recommendation comprises a report that includes an identified issue of the one or more respective issues, a number of incidents within a ranked cluster of the plurality of clusters associated with the identified issue, and the one or more service management operations.

12. A non-transitory, computer-readable medium, comprising instructions that, when executed by one or more processors, cause the one or more processors to:
receive, via a graphical user interface, one or more inputs associated with a data source;
extract historical incident report data for a plurality of incidents from the data source, wherein the historical incident report data comprises one or more text-based fields completed in natural language associated with each incident of the plurality of incidents and one or more value-based evaluation fields associated with each incident of the plurality of incidents;
group the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity between one or more text-based fields associated with each incident of the plurality of incidents and an additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
determine a respective evaluation value associated with each cluster of the plurality of clusters based on the additional degree of similarity between the one or more value-based evaluation fields associated with each incident of the plurality of incidents;
rank the plurality of clusters based at least on respective numbers of incidents in each cluster of the plurality of clusters and the respective evaluation value associated with each cluster;
identify one or more respective issues in common between each incident of each

Assignees

• Servicenow Inc

Inventors

• Walthers Bruce
• Kulkarni Abhay
• Ramachandran Mukund
• Koohmarey Darius

Classifications

• G06F16/285

  Clustering or classification · CPC title

• G06F40/279

  Recognition of textual entities · CPC title

• G06F40/205

  Parsing · CPC title

• G06F16/24578

  using ranking · CPC title

• G06Q30/016 Primary

  After-sales · CPC title