Identifying clusters for service management operations

A non-transitory computer-readable recording medium having stored thereon a program for a computer of a cluster identification system for service management operations, the program comprising instructions that when executed, cause the computer to:

• obtain client instance data including a plurality of incidents, each incident including a plurality of fields;
• select a first target field and an evaluation field from among the plurality of fields;
• group the plurality of incidents of the client instance data into a plurality of clusters based on a degree of a first natural language text similarity of respective first target fields in the plurality of incidents;
• determine, for each of the plurality of clusters, a first quality value based on the degree of the first natural language text similarity of respective first target fields in grouped incidents of the cluster from among the plurality of incidents, and based on respective evaluation fields in the grouped incidents of the cluster;
• select a second target field from among the plurality of fields, the second target field being different from the first target field;
• determine, for each of the plurality of clusters, a second quality value based on a degree of a second natural language text similarity of respective second target fields in the grouped incidents of the cluster from among the plurality of incidents, and based on the respective evaluation fields in the grouped incidents of the cluster;
• rank each of the plurality of clusters of the client instance data based on the respective first quality value and the respective second quality value of the cluster and a respective number of the grouped incidents of the cluster of the client instance data;
• and
• identify at least one of the ranked plurality of clusters to perform a service management operation associated with the cluster.

A cluster identification method for service management operations, comprising:

• obtaining, by one or more hardware processors, client instance data including a plurality of incidents, each incident including a plurality of fields;
• selecting, by the one or more hardware processors, a first target field and an evaluation field from among the plurality of fields;
• grouping, by the one or more hardware processors, the plurality of incidents of the client instance data into a plurality of clusters based on a degree of a first natural language text similarity of respective first target fields in the plurality of incidents;
• determining, by the one or more hardware processors and for each of the plurality of clusters, a first quality value based on the degree of the first natural language text similarity of respective first target fields in grouped incidents of the cluster from among the plurality of incidents, and based on respective evaluation fields in the grouped incidents of the cluster;
• selecting, by the one or more hardware processors, a second target field from among the plurality of fields, the second target field being different from the first target field;
• determining, by the one or more hardware processors and for each of the plurality of clusters, a second quality value based on a degree of a second natural language text similarity of respective second target fields in the grouped incidents of the cluster from among the plurality of incidents, and based on the respective evaluation fields in the grouped incidents of the cluster;
• ranking, by the one or more hardware processors, each of the plurality of clusters of the client instance data based on the respective first and the respective second quality value of the cluster and a respective number of the grouped incidents of the cluster of the client instance data;
• and
• identifying, by the one or more hardware processors, at least one of the ranked plurality of clusters to perform a service management operation associated with the cluster.