Identifying Discrepancies and Responsible Parties in a Customer Support System

Patent metadata

Field	Value
Publication number	US-2015379520-A1
Application number	US-201414319055-A
Country	US
Kind code	A1
Filing date	Jun 30, 2014
Priority date	Jun 30, 2014
Publication date	Dec 31, 2015
Grant date	—

Abstract

A mechanism is provided for improving customer satisfaction. Natural language processing (NLP) is utilized to identify information from a customer ticket that addresses a customer issue thereby forming one or more pieces of NLP identified information. Each piece of NLP identified information is analyzed to identify one or more responsible parties responsible for delays in addressing the customer issue. Responsive to identifying at least one responsible party responsible for at least one delay in addressing the customer issue, an indication flag is created for the responsible party. A notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue is then sent.

First claim

What is claimed is:

1 . A method, in a data processing system, for improving customer satisfaction, the method comprising:
utilizing, by a processor in the data processing system, natural language processing (NLP) to identify information from a customer ticket that addresses a customer issue thereby forming one or more pieces of NLP identified information; analyzing, by the processor, each piece of NLP identified information to identify one or more responsible parties responsible for delays in addressing the customer issue; responsive to identifying at least one responsible party responsible for at least one delay in addressing the customer issue, creating, by the processor, an indication flag for the responsible party; and sending, by the processor, a notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue.

2 . The method of claim 1 , further comprising:
identifying, by the processor, one or more previous customer tickets for the customer; utilizing, by the processor, NLP to identify historical information from the previous customer tickets, wherein the historical information is at least one of customer callbacks, previous ticket transfers, previous causes for the customer issues, or previous resolutions; and utilizing, by the processor, the historical information in analyzing each piece of NLP identified information to identify the one or more responsible parties responsible for delays in addressing the customer issue.

3 . The method of claim 1 , further comprising:
for each of the at least one responsible parties responsible for the at least one delay in addressing the customer issue:
prior to sending the notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue, determining, by the processor, a total of the identification flags for the at least one responsible party responsible for the at least one delay in addressing the customer issue exceeds a predetermined threshold; and
responsive to the total of the identification flags for the at least one responsible party responsible for the at least one delay in addressing the customer issue exceeding the predetermined threshold, sending, by the processor, the notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue.

4 . The method of claim 1 , wherein the notification is sent to at least one of an administrator for the at least one responsible party responsible for the at least one delay in addressing the customer issue or a customer representative of the customer.

5 . The method of claim 1 , wherein the information is from at least one support team or at least one support technician on the at least one support team.

6 . The method of claim 1 , wherein the NLP identifies, within statements associated with the customer ticket, parts of speech, and wherein the parts of speech are at least one of nouns, pronouns, verbs, adverbs, adjectives, prepositions, conjunctions, or interjections.

7 . The method of claim 1 , wherein the NLP identifies, within statements associated with the customer ticket grammar usages and wherein the grammar usages are at least one of nouns or pronouns that refer to products, verbs and adverbs associated with the nouns or pronouns, specific verbs or adverbs, negative connotations associated with the identified nouns or pronouns, or source of statement via a source code associated with statement.

8 . The method of claim 1 , wherein the NLP identifies key ticket elements where the customer ticket is transferred between support technicians on a single support team or between support teams and wherein transfers of the customer ticket are identified using source code field changes.

9 . The method of claim 1 , wherein the NLP identifies one or more of a cause for the customer ticket to be transferred, negations of one or more statements by one or more subsequent statements, or an ultimate resolution of the ticket.

10 . The method of claim 1 , wherein analyzing each piece of NLP identified information to identify one or more responsible parties responsible for delays in addressing the customer issue is based on identifying at least one discrepancy and wherein the at least one discrepancy is at least one of an initial incorrect forwarding of the ticket, an incorrect assessment of the issue by a support team, or an underlying resource issue caused by the customer's issue.

11 . A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
utilize natural language processing (NLP) to identify information from a customer ticket that addresses a customer issue thereby forming one or more pieces of NLP identified information; analyze each piece of NLP identified information to identify one or more responsible parties responsible for delays in addressing the customer issue; responsive to identifying at least one responsible party responsible for at least one delay in addressing the customer issue, create an indication flag for the responsible party; and send a notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue.

12 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
identify one or more previous customer tickets for the customer; utilize NLP to identify historical information from the previous customer tickets, wherein the historical information is at least one of customer callbacks, previous ticket transfers, previous causes for the customer issues, or previous resolutions; and utilize the historical information in analyzing each piece of NLP identified information to identify the one or more responsible parties responsible for delays in addressing the customer issue.

13 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
for each of the at least one responsible parties responsible for the at least one delay in addressing the customer issue:
prior to sending the notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue, determine a total of the identification flags for the at least one responsible party responsible for the at least one delay in addressing the customer issue exceeds a predetermined threshold; and
responsive to the total of the identification flags for the at least one responsible party responsible for the at least one delay in addressing the customer issue exceeding the predetermined threshold, send the notification of the at least one responsible party responsible for the at least one delay in addressing the customer issue.

14 . The computer program product of claim 11 , wherein the notification is sent to at least one of an administrator for the at least one responsible party responsible for the at least one delay in addressing the customer issue or a customer representative of the customer.

15 . The computer program product of claim 11 , wherein the information is from at least one support team or at least one support technician on the at least one support team.

16 . An apparatus comprising:
a processor; and a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the process

Assignees

• IBM

Inventors

• Allen Corville O
• Boggarapu Ramakrishna
• Muthukrishnan Ravi K
• Sherk Walker L

Classifications

• G06Q30/016 Primary

  After-sales · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F17/28

  Physics · mapped topic