Identifying application software performance problems using automated content-based semantic monitoring

A computer system comprising:

• a memory system;
• and
• a monitoring host communicatively coupled to the memory, wherein the host is configured to perform operations comprising;
• receiving, using natural language processing (NLP) algorithms of the host, training data comprising operational data and functionality data;
• wherein the operational data represents natural language descriptions of performance problems identified for an application computer program running a computing system;
• wherein the functionality data represents natural language descriptions of functional capabilities of the application computer program;
• using the NLP algorithms and a classifier of the host to extract features of the training data and use the extracted features to build a semantic correlation model comprising correlated data sets, wherein each of the correlated data sets comprises functionality data and operational data having a semantic correlation to functionality data;
• selecting at least one of the correlated data sets;
• and
• using the at least one of the correlated data sets to create an application monitoring (AM) algorithm configured to submit requests to and receive responses from the application computer program running on the computing system.

A computer program product for operating a monitoring host of a performance management system, the computer program product comprising a computer readable program stored on a computer readable storage medium, wherein the computer readable program, when executed on the host, causes the processors of the host to perform a method comprising:

• receiving, using natural language processing (NLP) algorithms of the host, training data comprising operational data and functionality data;
• wherein the operational data represents natural language descriptions of performance problems identified for an application computer program running a computing system;
• wherein the functionality data represents natural language descriptions of functional capabilities of the application computer program;
• using the NLP algorithms and a classifier of the host to extract features of the training data and use the extracted features to build a semantic correlation model comprising correlated data sets, wherein each of the correlated data sets comprises functionality data and operational data having a semantic correlation to functionality data;
• selecting at least one of the correlated data sets;
• and
• using the at least one of the correlated data sets to create an application monitoring (AM) algorithm configured to submit requests to and receive responses from the application computer program running on the computing system.