Predictive resolutions for tickets using semi-supervised machine learning

Abstract

Aspects of the subject disclosure may include, for example, a method in which a processing system collects information associated with trouble tickets each including a problem abstract and a log text. The method includes analyzing the log text to obtain a problem resolution for that ticket; defining ticket clusters according to the problem abstracts, and labeling the clusters. The processing system creates a library of the labeled clusters, each entry including a cluster label, a problem abstract for that cluster, and a resolution summary for that problem abstract, indicating a mapping of the problem abstract to the resolution summary for that cluster. The method includes training, based on the mapping, machine-learning applications for a predicted resolution summary for each cluster and for classifying a new ticket. The method includes assigning the new ticket to a cluster according to the classifying. Other embodiments are disclosed.

What is claimed is: 
     
         1 . A device comprising:
 a processing system including a processor; and   a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising:   analyzing information associated with a plurality of tickets, the information of each of the plurality of tickets relating to an issue affecting performance of a communication system;   obtaining a problem resolution associated with a problem abstract for each of the plurality of tickets;   defining a plurality of clusters in accordance with respective problem abstracts of the plurality of tickets, each of the plurality of clusters including at least one of the plurality of tickets;   generating for each of the plurality of clusters a mapping of a problem abstract pertaining to that cluster to a resolution summary pertaining to that cluster;   assigning a new ticket to a cluster according to a classifying application, the classifying application trained based on the mapping; and   analyzing tickets of at least one cluster using an electronic dispatcher application and reporting tool (EDART), wherein the EDART tool causes closure of a ticket in accordance with a policy, wherein responsive to a ticket in the at least one cluster being closed, the EDART tool causes attachment, to each open ticket in that cluster, of a message indicating a pending review by a user.   
     
     
         2 . The device of  claim 1 , wherein the information of each of the plurality of tickets includes the problem abstract and a log text, and wherein the obtaining the problem resolution for a ticket of the plurality of tickets comprises analyzing the log text for that ticket. 
     
     
         3 . The device of  claim 2 , wherein the analyzing comprises parsing the log text using natural language processing. 
     
     
         4 . The device of  claim 1 , wherein the issue relates to performance of the communication system during a past time period. 
     
     
         5 . The device of  claim 1 , wherein the operations further comprise labeling each of the plurality of clusters. 
     
     
         6 . The device of  claim 5 , wherein the operations further comprise creating a library of the labeled clusters having a plurality of entries, wherein each entry includes a cluster label, a problem abstract pertaining to that cluster, and a resolution summary pertaining to that problem abstract, thereby indicating the mapping of the problem abstract to the resolution summary for that cluster. 
     
     
         7 . The device of  claim 1 , wherein the operations further comprise:
 training, based on the mapping, a first machine-learning application for generating a predicted resolution summary for each of the plurality of clusters, and   training, based on the mapping, the classifying application, wherein the classifying application comprises a second machine-learning application comprising a multi-level classification model.   
     
     
         8 . The device of  claim 1 , wherein the assigning further comprises generating a number indicating a confidence level for the assigning. 
     
     
         9 . A method comprising:
 analyzing, by a processing system including a processor, information associated with a plurality of tickets, the information of each of the plurality of tickets relating to an issue affecting performance of a communication system;   obtaining, by the processing system, a problem resolution associated with a problem abstract for each of the plurality of tickets;   defining, by the processing system, a plurality of clusters in accordance with respective problem abstracts of the plurality of tickets, each of the plurality of clusters including at least one of the plurality of tickets;   generating, by the processing system, for each of the plurality of clusters a mapping of a problem abstract pertaining to that cluster to a resolution summary pertaining to that cluster;   assigning, by the processing system, a new ticket to a cluster according to a classification model, the classification model trained based on the mapping; and   analyzing, by the processing system, tickets of at least one cluster using an electronic dispatcher application and reporting tool (EDART), wherein the EDART tool causes closure of a ticket in accordance with a policy, wherein responsive to a ticket in the at least one cluster being closed, the EDART tool causes attachment, to each open ticket in that cluster, of a message indicating a pending review by a user.   
     
     
         10 . The method of  claim 9 , wherein the information of each of the plurality of tickets includes the problem abstract and a log text, and wherein the obtaining the problem resolution for a ticket of the plurality of tickets comprises analyzing the log text for that ticket. 
     
     
         11 . The method of  claim 9 , wherein the issue relates to performance of the communication system during a past time period. 
     
     
         12 . The method of  claim 9 , further comprising labeling, by the processing system, each of the plurality of clusters. 
     
     
         13 . The method of  claim 12 , further comprising creating, by the processing system, a library of the labeled clusters having a plurality of entries, wherein each entry includes a cluster label, a problem abstract pertaining to that cluster, and a resolution summary pertaining to that problem abstract, thereby indicating the mapping of the problem abstract to the resolution summary for that cluster. 
     
     
         14 . The method of  claim 9 , further comprising:
 training, by the processing system based on the mapping, a first machine-learning application for generating a predicted resolution summary for each of the plurality of clusters, and   training, by the processing system based on the mapping, the classification model, wherein the classification model comprises a second machine-learning application comprising a multi-level classification model.   
     
     
         15 . A non-transitory machine-readable medium that stores executable instructions that, when executed by a processing system including a processor, facilitate performance of operations comprising:
 analyzing information associated with a plurality of tickets, the information of each of the plurality of tickets relating to an issue affecting performance of a communication system;   obtaining a problem resolution associated with a problem abstract for each of the plurality of tickets;   defining a plurality of clusters in accordance with respective problem abstracts of the plurality of tickets, each of the plurality of clusters including at least one of the plurality of tickets;   generating for each of the plurality of clusters a mapping of a problem abstract pertaining to that cluster to a resolution summary pertaining to that cluster;   assigning a new ticket to a cluster according to an application, the application trained based on the mapping; and   analyzing tickets of at least one cluster using an electronic dispatcher application and reporting tool (EDART), wherein the EDART tool causes closure of a ticket in accordance with a policy, wherein responsive to a ticket in the at least one cluster being closed, the EDART tool causes attachment, to each open ticket in that cluster, of a message indicating a pending user review.   
     
     
         16 . The non-transitory machine-readable medium of  claim 15 , wherein the information of each of the plurality of tickets includes the problem abstract and a log text, and wherein the obtaining the problem resolution for a ticket of the plurality of tickets comprises analyzing the log text for that ticket. 
     
     
         17 . The non-transitory machine-readable medium of  claim 15 , wherein the issue relates to performance of the communication system during a past time period. 
     
     
         18 . The non-transitory machine-readable medium of  claim 15 , wherein the operations further comprise labeling each of the plurality of clusters. 
     
     
         19 . The non-transitory machine-readable medium of  claim 18 , wherein the operations further comprise creating a library of the labeled clusters having a plurality of entries, wherein each entry includes a cluster label, a problem abstract pertaining to that cluster, and a resolution summary pertaining to that problem abstract, thereby indicating the mapping of the problem abstract to the resolution summary for that cluster. 
     
     
         20 . The non-transitory machine-readable medium of  claim 15 , wherein the operations further comprise:
 training, based on the mapping, a first machine-learning application for generating a predicted resolution summary for each of the plurality of clusters, and   training, based on the mapping, the application, wherein the application comprises a second machine-learning application comprising a multi-level classification model.