Artificial intelligence based problem descriptions

Abstract

Techniques regarding providing artificial intelligence problem descriptions are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can include, at least: a query component that generates key performance indicators from a query, determines a subset of key performance indicators that individually have a performance below a threshold, and maps the subset of key performance indicators to operational metrics; a learning component that generates, using artificial intelligence, problem descriptions from one or more of the subset of key performance indicators or the operational metrics and transmits the problem descriptions to a database.

What is claimed is: 
     
         1 . A system, comprising:
 a memory that stores computer-executable components;   a processor, operably coupled to the memory, and that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
 a query component that generates contextual derivations from key performance indicators based on a query associated with a system under test; 
 a learning component that uses an artificial intelligence (AI) model to generate problem descriptions from the key performance indicators, wherein training data used to train the AI model comprises information associated with known key performance indicators comprising key performance parameters mapped to known problem descriptions; and 
 a content component that provides a recommendation to an entity, based on the problem descriptions, at a display device associated with the entity, wherein the entity uses the recommendation to correct a problem associated with the system under test. 
   
     
     
         2 . The system of  claim 1 , wherein the learning component further generates the problem descriptions by computing at least one of: one or more correlations between a first subset of the key performance indicators and a second subset of the key performance indicators, a correlation between a subset of the key performance indicators and a subset of operational metrics, or a correlation between a first subset of the operational metrics and a second subset of the operational metrics. 
     
     
         3 . The system of  claim 1 , wherein the content component derives information from one or more enterprise data sources to provide an analysis of one or more problems associated with the system under test. 
     
     
         4 . The system of  claim 3 , wherein the content component relates the one or more problems to one or more enterprise health controls. 
     
     
         5 . The system of  claim 1 , wherein the AI model includes a recurrent neural network. 
     
     
         6 . The system of  claim 5 , wherein the recurrent neural network comprises a long-short term memory neural network. 
     
     
         7 . The system of  claim 1 , wherein the query component computes the key performance indicators by classifying the query using a multi-label classifier. 
     
     
         8 . The system of  claim 7 , wherein a user trains the multi-label classifier by validating labels predicted by the multi-label classifier for training data comprising labeled queries and unlabeled queries. 
     
     
         9 . The system of  claim 1 , wherein the query component computes the key performance indicators in an automatic manner or a semi-automatic manner, and wherein the generating the problem descriptions provides a real-time health check of the system under test. 
     
     
         10 . A computer-implemented method, comprising:
 generating, by a system operatively coupled to a processor, contextual derivations from key performance indicators based on a query associated with a system under test;   generating, by the system, using an artificial intelligence (AI) model, problem descriptions from the key performance indicators, wherein training data used to train the AI model comprises information associated with known key performance indicators comprising key performance parameters mapped to known problem descriptions; and   providing, by the system, a recommendation to an entity at a display device associated with the entity, based on the problem descriptions, wherein the entity uses the recommendation to correct a problem associated with the system under test.   
     
     
         11 . The computer-implemented method of  claim 10 , further comprising:
 generating, by the system, the problem descriptions by computing at least one of: one or more correlations between a first subset of the key performance indicators and a second subset of the key performance indicators, a correlation between a subset of the key performance indicators and a subset of operational metrics, or a correlation between a first subset of the operational metrics and a second subset of the operational metrics.   
     
     
         12 . The computer-implemented method of  claim 10 , further comprising:
 deriving, by the system, information from one or more enterprise data sources to provide an analysis of one or more problems associated with the system under test and relate the one or more problems to one or more enterprise health controls.   
     
     
         13 . The computer-implemented method of  claim 10 , wherein the AI model includes a recurrent neural network, and wherein the recurrent neural network comprises a long-short term memory neural network. 
     
     
         14 . The computer-implemented method of  claim 10 , further comprising:
 computing, by the system, the key performance indicators by classifying the query using a multi-label classifier.   
     
     
         15 . The computer-implemented method of  claim 14 , wherein the multi-label classifier is trained by a user by validating labels predicted by the multi-label classifier for training data comprising labeled queries and unlabeled queries. 
     
     
         16 . A computer program product for automated problem generation using artificial intelligence, comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
 generate, by the processor, contextual derivations from key performance indicators based on a query associated with a system under test;   generate, by the processor, using an artificial intelligence (AI) model, problem descriptions from the key performance indicators, wherein training data used to train the AI model comprises information associated with known key performance indicators comprising key performance parameters mapped to known problem descriptions; and   provide, by the processor, a recommendation to an entity at a display device associated with the entity, based on the problem descriptions, wherein the entity uses the recommendation to correct a problem associated with the system under test.   
     
     
         17 . The computer program product of  claim 16 , wherein the program instructions are further executable by the processor to cause the processor to:
 generate, by the processor, the problem descriptions by computing at least one of: one or more correlations between a first subset of the key performance indicators and a second subset of the key performance indicators, a correlation between a subset of the key performance indicators and a subset of operational metrics, or a correlation between a first subset of the operational metrics and a second subset of the operational metrics.   
     
     
         18 . The computer program product of  claim 16 , wherein the program instructions are further executable by the processor to cause the processor to:
 derive, by the processor, information from one or more enterprise data sources to provide an analysis of one or more problems associated with the system under test and relate the one or more problems to one or more enterprise health controls.   
     
     
         19 . The computer program product of  claim 16 , wherein the AI model includes a recurrent neural network, and wherein the recurrent neural network comprises a long-short term memory neural network. 
     
     
         20 . The computer program product of  claim 16 , wherein the program instructions are further executable by the processor to cause the processor to:
 compute, by the processor, the key performance indicators by classifying the query using a multi-label classifier.   
     
     
         21 . A system, comprising:
 a memory that stores computer-executable components;   a processor, operably coupled to the memory, and that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
 a query component that generates contextual derivations from key performance indicators based on a query associated with a system under test; 
 a learning component that uses an artificial intelligence (AI) model to generate problem descriptions from the key performance indicators by computing one or more correlations between a first subset of the key performance indicators and a second subset of the key performance indicators, wherein training data used to train the AI model comprises information associated with known key performance indicators comprising key performance parameters mapped to known problem descriptions; and 
 a content component that provides a recommendation to an entity, based on the problem descriptions, at a display device associated with the entity, wherein the entity uses the recommendation to correct a problem associated with the system under test. 
   
     
     
         22 . The system of  claim 21 , wherein the AI model includes a recurrent neural network, and wherein the recurrent neural network comprises a long-short term memory neural network. 
     
     
         23 . The system of  claim 21 , wherein the query component computes key performance indicators by classifying the query using a multi-label classifier. 
     
     
         24 . A computer-implemented method, comprising:
 generating, by a system operatively coupled to a processor, contextual derivations from key performance indicators based on a query associated with a system under test;   generating, by the system, using an artificial intelligence (AI) model, problem descriptions from the key performance indicators by computing one or more correlations between a first subset of the key performance indicators and a second subset of the key performance indicators, wherein training data used to train the AI model comprises information associated with known key performance indicators comprising key performance parameters mapped to known problem descriptions; and   providing, by the system, a recommendation to an entity at a display device associated with the entity, based on the problem descriptions, wherein the entity uses the recommendation to correct a problem associated with the system under test.   
     
     
         25 . The computer-implemented method of  claim 24 , further comprising:
 computing, by the system, the key performance indicators by classifying the query using a multi-label classifier.