Identifying related messages in a natural language interaction

Abstract

By executing a natural language processing model on a set of natural language text describing a first engagement, a set of characteristics of the first engagement is generated. By executing the natural language processing model on a set of natural language text describing a future engagement, a set of characteristics of the future engagement is generated. The first engagement is determined to be above a threshold similarity with the future engagement. Using the skillset used in performing the first engagement, a required skillset of the future engagement is forecasted. By executing the natural language processing model on a set of natural language text describing a current skillset, a set of characteristics of the current skillset is generated. Using the required skillset of the future engagement and the set of characteristics of the current skillset, a learning path is generated.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 constructing a software application interfacing with a training management system, the software application comprising a forecasting function enhancing a training selection functionality of the training management system by:   determining, using a first set of characteristics extracted from a natural language text of a first engagement and a future set of characteristics extracted from an image data describing a future engagement, that the first engagement is above a threshold similarity with the future engagement;   forecasting, using a skillset used in performing the first engagement, a required skillset of the future engagement;   generating a set of steps to transform a current skillset to the required skillset.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the first engagement comprises a completed engagement. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the first engagement comprises an ongoing engagement. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the first set of characteristics comprises the skillset used in performing the first engagement. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein the first set of characteristics comprises a level of a skill of the skillset used in performing the first engagement. 
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 augmenting, by executing a convolutional neural network model on a set of image data describing the first engagement, the first set of characteristics.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein the future set of characteristics is extracted at least in part by:
 executing a convolutional neural network model on the image data describing the future engagement.   
     
     
         8 . The computer-implemented method of  claim 1 , further comprising:
 performing a clustering technique on the first set of characteristics and the future set of characteristics to determine similarity between with the first engagement and the future engagement.   
     
     
         9 . A computer program product for natural language document based skill requirement forecasting, the computer program product comprising:
 one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
 program instructions to construct a software application interfacing with a training management system, the software application comprising a forecasting function enhancing a training selection functionality of the training management system by: 
 program instructions to determine, using a first set of characteristics extracted from a natural language text of a first engagement and a future set of characteristics extracted from an image data describing a future engagement, that the first engagement is above a threshold similarity with the future engagement; 
 program instructions to forecast, using a skillset used in performing the first engagement, a required skillset of the future engagement; 
 program instructions to generate a set of steps to transform a current skillset to the required skillset. 
   
     
     
         10 . The computer program product of  claim 9 , wherein the first engagement comprises a completed engagement. 
     
     
         11 . The computer program product of  claim 9 , wherein the first engagement comprises an ongoing engagement. 
     
     
         12 . The computer program product of  claim 9 , wherein the first set of characteristics comprises the skillset used in performing the first engagement. 
     
     
         13 . The computer program product of  claim 9 , wherein the first set of characteristics comprises a level of a skill of the skillset used in performing the first engagement. 
     
     
         14 . The computer program product of  claim 9 , further comprising:
 program instructions to augment, by executing a convolutional neural network model on a set of image data describing the first engagement, the first set of characteristics.   
     
     
         15 . The computer program product of  claim 9 , wherein the future set of characteristics is extracted at least in part by:
 program instructions to execute a convolutional neural network model on the image data describing the future engagement.   
     
     
         16 . The computer program product of  claim 9 , wherein the stored program instructions are stored in the at least one of the one or more storage media of a local data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system. 
     
     
         17 . The computer program product of  claim 9 , wherein the stored program instructions are stored in the at least one of the one or more storage media of a server data processing system, and wherein the stored program instructions are downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system. 
     
     
         18 . The computer program product of  claim 9 , wherein the computer program product is provided as a service in a cloud environment. 
     
     
         19 . A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
 one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
 program instructions to construct a software application interfacing with a training management system, the software application comprising a forecasting function enhancing a training selection functionality of the training management system by: 
 program instructions to determine, using a first set of characteristics extracted from a natural language text of a first engagement and a future set of characteristics extracted from an image data describing a future engagement, that the first engagement is above a threshold similarity with the future engagement; 
 program instructions to forecast, using a skillset used in performing the first engagement, a required skillset of the future engagement; 
 program instructions to generate a set of steps to transform a current skillset to the required skillset. 
   
     
     
         20 . The computer system of  claim 19 , wherein the first engagement comprises a completed engagement.