Identifying clusters for service management operations

Patent metadata

Field	Value
Publication number	US-2018365700-A1
Application number	US-201816059867-A
Country	US
Kind code	A1
Filing date	Aug 9, 2018
Priority date	May 5, 2017
Publication date	Dec 20, 2018
Grant date	—

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 method for analyzing incidents based on natural language text similarity to identify similar types of incidents, the method comprising:
receiving, via a graphical user interface, input values for a cluster identification operation, wherein the input values comprise a client instance identifier that identifies a client instance and a target field identifier that identifies a text-based field completed in natural language; extracting historical incident report data for a plurality of incidents from one or more databases using the client instance identifier; grouping the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity of respective target fields in the plurality of incidents; ranking the plurality of clusters based at least on respective numbers of grouped incidents in individual clusters of the plurality of clusters; generating text descriptions for respective clusters of the plurality of clusters; and providing for display a graphical representation of the plurality of clusters that highlights similar types of incidents by volume, wherein the graphical representation includes the respective text descriptions and the respective numbers of grouped incidents for the respective clusters, and wherein the respective clusters are arranged within the graphical representation based at least in part on the ranking.

2 . The method of claim 1 , wherein the input values further comprise a time period, and wherein extracting the historical incident report data for the plurality of incidents comprises extracting historical incident for a plurality of incidents corresponding to the time period.

3 . The method of claim 1 , wherein the input values further comprise a geographic region, and wherein extracting the historical incident report data for the plurality of incidents comprises extracting historical incident for a plurality of incidents corresponding to the geographic region.

4 . The method of claim 1 , wherein the text-based field is an incident description field.

5 . The method of claim 1 , wherein the input values further comprise a tunable input parameter n defining a total number of clusters, and wherein grouping the plurality of incidents into the plurality of clusters comprises grouping the plurality of incidents into n clusters.

6 . The method of claim 1 , further comprising:
determining, based on the input values, a number of incidents in the plurality of incidents; and prior to performing the cluster identification operation, providing for display via the graphical user interface the determined number of incidents as an output value.

7 . The method of claim 1 , further comprising:
determining respective quality values for clusters of the plurality of clusters; and determining whether or not to regroup the plurality of incidents based on the determined quality values.

8 . The method of claim 1 , wherein generating the text descriptions comprises generating text descriptions for respective clusters based on respective target fields of incidents included in the clusters.

9 . The method of claim 1 , wherein the respective clusters are arranged within the graphical representation from highest respective number of grouped incidents to lowest number of grouped incidents.

10 . The method of claim 1 , wherein the graphical representation of the plurality of clusters comprises graphic elements corresponding to respective individual clusters of the plurality of clusters, with sizes of the graphical elements being proportional to the respective numbers of grouped incidents in the individual clusters.

11 . A system comprising:
one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform functions comprising:
receiving input values for a cluster identification operation, wherein the input values comprise a client instance identifier that identifies a client instance and a target field identifier that identifies a text-based field completed in natural language,
extracting historical incident report data for a plurality of incidents from one or more databases using the client instance identifier,
grouping the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity of respective target fields in the plurality of incidents,
ranking the plurality of clusters based at least on respective numbers of grouped incidents in individual clusters of the plurality of clusters,
generating text descriptions for respective clusters of the plurality of clusters, and
providing for display a graphical representation of the plurality of clusters that highlights similar types of incidents by volume, wherein the graphical representation includes the respective text descriptions and the respective numbers of grouped incidents for the respective clusters, and wherein the respective clusters are arranged within the graphical representation based at least in part on the ranking.

12 . The system of claim 11 , wherein the input values further comprise a time period, and wherein extracting the historical incident report data for the plurality of incidents comprises extracting historical incident for a plurality of incidents corresponding to the time period.

13 . The system of claim 11 , wherein the text-based field is an incident description field.

14 . The system of claim 11 , wherein the input values further comprise a tunable input parameter n defining a total number of clusters, and wherein grouping the plurality of incidents into the plurality of clusters comprises grouping the plurality of incidents into n clusters.

15 . The system of claim 11 , wherein the functions further comprise:
determining, based on the input values, a number of incidents in the plurality of incidents; and prior to performing the cluster identification operation, providing for display the determined number of incidents as an output value.

16 . The system of claim 11 , wherein generating the text descriptions comprises generating text descriptions for respective clusters based on respective target fields of incidents included in the clusters.

17 . The system of claim 11 , wherein the respective clusters are arranged within the graphical representation from highest respective number of grouped incidents to lowest number of grouped incidents.

18 . The system of claim 11 , wherein the graphical representation of the plurality of clusters comprises graphic elements corresponding to respective individual clusters of the plurality of clusters, with sizes of the graphical elements being proportional to the respective numbers of grouped incidents in the individual clusters.

19 . A method for analyzing incidents based on natural language text similarity to identify similar types of incidents, the method comprising:
receiving input values for a cluster identification operation, wherein the input values identify (i) a plurality of incidents having a plurality of fields and (ii) a target field of the plurality of fields, wherein the target field is a text-based field completed in natural language; obtaining historical report data for the plurality of incidents; grouping the plurality of incidents into a plurality of clusters based on a degree of natural language text similarity of respective target fields in the plurality of incidents; ranking the plurality of clusters based at least on respective numbers of grouped incidents in individu

Assignees

• Servicenow Inc

Inventors

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

Classifications

• G06F40/279

  Recognition of textual entities · CPC title

• G06F40/186

  Templates · CPC title

• G06F16/285

  Clustering or classification · CPC title

• G06Q30/016 Primary

  After-sales · CPC title

• G06F16/24578

  using ranking · CPC title