Predictive monitoring of software application frameworks using machine-learning-based techniques
Systems and methods provide techniques for more effective and efficient predictive monitoring of a software application framework. In response, embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to enable effective and efficient predictive monitoring of a software application framework using incident signatures for the software application that are generated by using a natural language processing machine learning framework, a structured data processing machine learning model, and an incident severity level detection machine learning model.
1 . An apparatus for predictive monitoring of a software application framework, the apparatus comprising at least one processor and at least one non-transitory memory comprising a computer program code, the at least one non-transitory memory and the computer program code configured to, with the at least one processor, cause the apparatus to:
generate a natural language feature data object for a software incident data object by applying a natural language feature extraction machine learning model to the software incident data object;
generate a structured data feature data object for the software incident data object by applying a structured data feature extraction machine learning model to the software incident data object;
generate, based on the natural language feature data object and the structured data feature data object, one or more incident signatures for the software application framework, wherein the one or more incident signatures describe one or more inferred incident properties for the software application framework that are based on at least one of: first severity level software incidents, second severity level software incidents, precision rates, recall rates, or F-measures, wherein the one or more inferred incident properties comprise at least a count of the first severity level software incidents associated with the software application framework and a count of the second severity level software incidents associated with the software application framework; and
perform one or more prediction-based actions based on the one or more incident signatures.
2 . The apparatus of claim 1 , wherein the software incident data object comprises one or more natural language data fields, wherein the natural language feature extraction machine learning model is configured to process the one or more natural language data fields to generate the natural language feature data object.
3 . The apparatus of claim 2 , wherein the one or more natural language data fields comprise a message field.
4 . The apparatus of claim 2 , wherein the software incident data object comprises one or more structured data fields, wherein the structured data feature extraction machine learning model is configured to process the one or more structured data fields to generate the structured data feature data object.
5 . The apparatus of claim 4 , wherein the one or more structured data fields comprise a timestamp field for the software incident data object.
6 . The apparatus of claim 4 , wherein the one or more structured data fields comprise a window-adjusted timestamp that is determined based on a sliding window for the software incident data object, wherein the sliding window comprises a predefined number of temporally adjacent software incident data objects for the software incident data object.
7 . The apparatus of claim 1 , wherein performing the one or more prediction-based actions comprises generating user interface data for a prediction output user interface, wherein the user interface data is representative of a predicted incident severity level for the software incident data object.
8 . The apparatus of claim 7 , wherein the predicted incident severity level is generated, using an incident severity level detection machine learning model, based on the natural language feature data object and the structured data feature data object.
9 . The apparatus of claim 1 , wherein performing the one or more prediction-based actions comprises causing display of a prediction output user interface comprising the one or more incident signatures.
10 . The apparatus of claim 1 , wherein performing the one or more prediction-based actions comprises performing one or more automated system maintenance operations based on the one or more incident signatures.
11 . A computer-implemented method for predictive monitoring of a software application framework, the computer-implemented method comprising:
generating a natural language feature data object for a software incident data object by applying a natural language feature extraction machine learning model to the software incident data object;
generating a structured data feature data object for the software incident data object by applying a structured data feature extraction machine learning model to the software incident data object;
generating, based on the natural language feature data object and the structured data feature data object, one or more incident signatures for the software application framework, wherein the one or more incident signatures describe one or more inferred incident properties for the software application framework that are based on at least one of: first severity level software incidents, second severity level software incidents, precision rates, recall rates, or F-measures, wherein the one or more inferred incident properties comprise at least a count of the first severity level software incidents associated with the software application framework and a count of the second severity level software incidents associated with the software application framework; and
performing one or more prediction-based actions based on the one or more incident signatures.
12 . The computer-implemented method of claim 11 , wherein the software incident data object comprises one or more natural language data fields, wherein the natural language feature extraction machine learning model is configured to process the one or more natural language data fields to generate the natural language feature data object.
13 . The computer-implemented method of claim 12 , wherein the one or more natural language data fields comprise a message field.
14 . The computer-implemented method of claim 12 , wherein the software incident data object comprises one or more structured data fields, wherein the structured data feature extraction machine learning model is configured to process the one or more structured data fields to generate the structured data feature data object.
15 . The computer-implemented method of claim 14 , wherein the one or more structured data fields comprise a timestamp field for the software incident data object.
16 . The computer-implemented method of claim 14 , wherein the one or more structured data fields comprise a window-adjusted timestamp that is determined based on a sliding window for the software incident data object, wherein the sliding window comprises a predefined number of temporally adjacent software incident data objects for the software incident data object.
17 . The computer-implemented method of claim 11 , wherein performing the one or more prediction-based actions comprises generating user interface data for a prediction output user interface, wherein the user interface data is representative of a predicted incident severity level for the software incident data object.
18 . The computer-implemented method of claim 17 , wherein the predicted incident severity level is generated, using an incident severity level detection machine learning model, based on the natural language feature data object and the structured data feature data object.
19 . The computer-implemented method of claim 11 , wherein performing the one or more prediction-based actions comprises causing display of a prediction output user interface comprising the one or more incident signatures.
20 . The computer-implemented method of claim 11 , wherein performing the one or more prediction-based actions comprises performing one or more automated system maintenance operations based on the one or more incident signatures.