Resolution and pipelining of helpdesk tickets needing resolutions from multiple groups
A help desk management system uses segment partitioning and matching of each identified segment to a suitable problem and resolver group and then sequencing the partitioned segments based on sentiment analysis and sequence mining on historical tickets and audit logs to actuate effective resolution and pipelining of helpdesk tickets needing resolutions from multiple resolver groups. The helpdesk tickets can be in the form of e-mails.
1. A method of resolving helpdesk ticket messages received electronically by a computer, in which a single helpdesk ticket message requires resolutions from multiple resolver groups, the method comprising the computer executing program instructions of:
identifying at least two problem entities from within text of the single helpdesk ticket message received from a user;
identifying topics within each of the at least two identified problem entities from within the text of the single helpdesk ticket message, said identifying topics identifying at least two topics within the single helpdesk ticket message;
parsing the text of the single helpdesk ticket message into subsections based on the identified topics of the at least two identified problem entities;
assigning each subsection of text of the single helpdesk ticket message to a single relevant resolver group, wherein at least a first single relevant resolver group assigned to one subsection of text is different than at least a second single relevant group assigned to another subsection of text of the single helpdesk ticket message;
determining a priority of each identified topic within the single helpdesk ticket message by ascertaining a sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message, said ascertaining the sequence of resolver groups comprising determining a sequence inferred from text of the single helpdesk ticket message based on an interdependencies between resolver groups; and
based on the priority of each identified topic of the identified topics of the at least two problem entities within the single helpdesk ticket message, sending the single helpdesk ticket to the single relevant resolver group associated with the identified topic with a highest priority.
2. The method of claim 1 , wherein said ascertaining the sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message further comprises using sentiment analysis and classifier training based on historically resolved helpdesk ticket messages.
3. A computer program product for resolving helpdesk ticket messages, in which a single helpdesk ticket message requires resolutions from multiple resolver groups by a computer comprising at least one processor, one or more memories, one or more computer readable storage media, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the computer to perform a method comprising:
identifying, by the computer, at least two problem entities from within text of the single helpdesk ticket message received from a user;
identifying, by the computer, topics within each of the at least two identified problem entities from within the text of the single helpdesk ticket message, said identifying topics identifying at least two topics within the single helpdesk ticket message;
parsing, by the computer, the text of the single helpdesk ticket message into subsections based on the identified topics of the at least two identified problem entities;
assigning, by the computer, each subsection of text of the single helpdesk ticket message to a single relevant resolver group, wherein at least a first single relevant resolver group assigned to one subsection of text is different than at least a second single relevant group assigned to another subsection of text of the single helpdesk ticket message;
determining a priority of each identified topic within the single helpdesk ticket message by ascertaining a sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message, said ascertaining the sequence of resolver groups comprising determining a sequence inferred from text of the single helpdesk ticket message based on an interdependencies between resolver groups; and
based on the priority of each identified topic of the identified topics of the at least two problem entities within the single helpdesk ticket message, sending, by the computer, the single helpdesk ticket to the single relevant resolver group associated with the identified topic with a highest priority.
4. The computer program product of claim 3 , wherein said ascertaining the sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message further comprises using sentiment analysis and classifier training based on historically resolved helpdesk ticket messages.
5. A computer system for resolving helpdesk ticket messages, in which a single helpdesk ticket message requires resolutions from multiple resolver groups using a computer comprising at least one processor, one or more memories, one or more computer readable storage media having program instructions executable by the computer to perform the program instructions comprising:
identifying, by the computer, at least two problem entities from within text of the single helpdesk ticket message received from a user;
identifying, by the computer, topics within each of the at least two identified problem entities from within the text of the single helpdesk ticket message, said identifying topics identifying at least two topics within the single helpdesk ticket message;
parsing, by the computer, the text of the single helpdesk ticket message into subsections based on the identified topics of the at least two identified problem entities;
assigning, by the computer, each subsection of text of the single helpdesk ticket message to a single relevant resolver group, wherein at least a first single relevant resolver group assigned to one subsection of text is different than at least a second single relevant group assigned to another subsection of text of the single helpdesk ticket message;
determining a priority of each identified topic within the single helpdesk ticket message by ascertaining a sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message, said ascertaining the sequence of resolver groups comprising determining a sequence inferred from text of the single helpdesk ticket message based on an interdependencies between resolver groups; and
based on the priority of each identified topic of the identified topics of the at least two problem entities within the single helpdesk ticket message, sending, by the computer, the single helpdesk ticket to the single relevant resolver group associated with the identified topic with a highest priority.
6. The computer system of claim 5 , wherein said ascertaining the sequence of resolver groups sequentially ordered according to a priority of utilizing the resolver groups to resolve the problem entities within the single helpdesk ticket message further comprises using sentiment analysis and classifier training based on historically resolved helpdesk ticket messages.
7. The method of claim 1 , wherein said ascertaining the sequence of resolver groups further comprises determining a natural sequence of problem resolution mined from audit logs or ticket assignment history.
8. The method of claim 1 , wherein said ascertaining the sequence of resolver groups further comprises determining a user defined priority inferred from the single helpdesk ticket message at runtime.
9. The method of claim 1 , wherein said ascertaining the sequence of resolver groups further comprises determining a computer-aided engineering system predicted severity of the individual problem entities based on a classifier model trained on historically resolved helpdesk ticket messages.
10. The computer program product of claim 3 , wherein said ascertaining the sequence of resolver groups further comprises determining a natural sequence of problem resolution mined from audit logs or ticket assignment history.
11. The computer program product of claim 3 , wherein said ascertaining the sequence of resolver groups further comprises determining a user defined priority inferred from the single helpdesk ticket message at runtime.
12. The computer program product of claim 3 , said ascertaining the sequence of resolver groups further comprises determining a computer-aided engineering system predicted severity of the individual problem entities based on a classifier model trained on historically resolved helpdesk ticket messages.
13. The computer system of claim 5 , wherein said ascertaining the sequence of resolver groups further comprises determining a natural sequence of problem resolution mined from audit logs or ticket assignment history.
14. The computer system of claim 5 , wherein said ascertaining the sequence of resolver groups further comprises determining a user defined priority inferred from the single helpdesk ticket message at runtime.
15. The computer system of claim 5 , wherein said ascertaining the sequence of resolver groups further comprises determining a computer-aided engineering system predicted severity of the individual problem entities based on a classifier model trained on historically resolved helpdesk ticket messages.