Management system for software incidents

A system comprising:

• a storage device configured to store an incident report comprising a textual description of an incident involving a software system;
• and
• one or more processors implemented in circuitry and configured to:
• receive an incident report comprising a textual description of an incident;
• generate a regularized incident report in which out-of-vocabulary terms in the received incident report are replaced with in-vocabulary terms;
• determine importance measures for a plurality of incident report terms, wherein each of the incident report terms is in the regularized incident report;
• generate an incident matrix in which similarity values are defined for combinations of terms in the incident report and terms in a predetermined term set;
• generate an incident vector based on the incident matrix and the importance measures for the terms in the incident report;
• apply one or more machine learning (ML) models that identify, based on the incident vector, relevant software support records and/or software modules of the software system, wherein the relevant software support records and the software modules are potentially relevant to the incident;
• and
• output data identifying relevant software support records and/or software modules.

A non-transitory computer-readable storage medium comprising instructions that, when executed, cause one or more processors of a computing system to:

• receive an incident report comprising a textual description of an incident involving a software system;
• generate a regularized incident report in which out-of-vocabulary terms in the received incident report are replaced with in-vocabulary terms;
• determine importance measures for a plurality of incident report terms, wherein each of the incident report terms is in the regularized incident report;
• generate an incident matrix in which similarity values are defined for combinations of terms in the incident report and terms in a predetermined term set;
• generate an incident vector based on the incident matrix and the importance measures for the terms in the incident report;
• apply one or more machine learning (ML) models that identify, based on the incident vector, relevant software support records and/or software modules of the software system, wherein the relevant software support records and the software modules are potentially relevant to the incident;
• and
• output data identifying relevant software support records and/or software modules.