Cognitive analysis based prioritization for support tickets

Patent metadata

Field	Value
Publication number	US-2019158366-A1
Application number	US-201715815955-A
Country	US
Kind code	A1
Filing date	Nov 17, 2017
Priority date	Nov 17, 2017
Publication date	May 23, 2019
Grant date	—

Abstract

A prioritization system and method may include receiving a customer support ticket from a user, wherein a default severity level associated with the customer support ticket is assigned, calculating, by the processor, a user sentiment score and a user personality score by applying a sentiment analysis and a personality analysis to user-specific data, applying, by the processor, a weighting scheme to the user sentiment score and the user personality score to generate a weighted priority score associated with the customer support ticket, adjusting, by the processor, the default severity level according to the weighted priority score to determine an adjusted severity level of the customer support ticket, and prioritizing, by the processor, the customer support ticket among other customer support tickets based on the adjusted severity level of the customer support ticket.

First claim

1 . A method for prioritizing a customer support ticket system, the method comprising:
receiving, by a processor of a computing system, a customer support ticket from a user, wherein a default severity level associated with the customer support ticket is assigned; calculating, by the processor, a user sentiment score and a user personality score by applying a sentiment analysis and a personality analysis to user-specific data; applying, by the processor, a weighting scheme to the user sentiment score and the user personality score to generate a weighted priority score associated with the customer support ticket, adjusting, by the processor, the default severity level to an adjusted severity level according to the weighted priority score; and prioritizing, by the processor, the customer support ticket among other customer support tickets based on the adjusted severity level of the customer support ticket.

2 . The method of claim 1 , wherein the user specific data is a member of the group consisting of: a user activity and a user shared content across one or more social network platforms, a voice data of the user, a content of the customer support ticket, and a customer relationship management (CRM) data.

3 . The method of claim 2 , wherein:
the user activity and the user shared content relates to a topic associated with the customer support ticket; the voice data of the user is associated with at least one of: one or more previous support calls, a current support call, and a combination of the one or more previous support calls and the current call; the CRM data includes a customer lifetime value (CLV), a contact information of the user, an organization associated with the user, an experience level of the user, and a total number of accounts associated with the user; and the content of the customer support ticket includes a recency of the customer support ticket, a frequency of reported support tickets, a type of account, a number of times the user has issued a support ticket for a same issue, a component involved in the customer support ticket, a time of day, a day of a week, an amount of downtime, and account specific information.

4 . The method of claim 3 , wherein analyzing the user activity and shared content includes analyzing a history of shared content of the user for a specified data range measured from receiving the customer support ticket.

5 . The method of claim 1 , wherein the sentiment analysis determines a sentiment of the user toward a topic associated with the customer support ticket, and an emotional status of the user at a time of submitting the customer support ticket.

6 . The method of claim 1 , wherein the personality analysis determines a personality of the user, including a patience level of the user, a technical skill level of the user, and a communication style of the user.

7 . The method of claim 1 , wherein one or more data science prediction algorithms are used to analyze a plurality of sentiment inputs resulting from the sentiment analysis and a plurality of personality inputs resulting from the personality analysis to determine a weight of the weighting scheme to be applied to the user sentiment score and the user personality score, further wherein the weight is based on an impact on a severity of the customer support ticket.

8 . A computer system, comprising:
a processor; a memory device coupled to the processor; and a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method for prioritizing a customer support ticket system, the method comprising:
receiving, by a processor of a computing system, a customer support ticket from a user, wherein a default severity level associated with the customer support ticket is assigned;
calculating, by the processor, a user sentiment score and a user personality score by applying a sentiment analysis and a personality analysis to user-specific data;
applying, by the processor, a weighting scheme to the user sentiment score and the user personality score to generate a weighted priority score associated with the customer support ticket;
adjusting, by the processor, the default severity level to an adjusted severity level according to the weighted priority score; and
prioritizing, by the processor, the customer support ticket among other customer support tickets based on the adjusted severity level of the customer support ticket.

9 . The computer system of claim 8 , wherein the user specific data is a member of the group consisting of: a user activity and a user shared content across one or more social network platforms, a voice data of the user, a content of the customer support ticket, and a customer relationship management (CRM) data.

10 . The computer system of claim 9 , wherein:
the user activity and the user shared content relates to a topic associated with the customer support ticket; the voice data of the user is associated with at least one of: one or more previous support calls, a current support call, and a combination of the one or more previous support calls and the current call; the CRM data includes a customer lifetime value (CLV), a contact information of the user, an organization associated with the user, an experience level of the user, and a total number of accounts associated with the user; and the content of the customer support ticket includes a recency of the customer support ticket, a frequency of reported support tickets, a type of account, a number of times the user has issued a support ticket for a same issue, a component involved in the customer support ticket, a time of day, a day of a week, an amount of downtime, and account specific information.

11 . The computer system of claim 10 , wherein analyzing the user activity and shared content includes analyzing a history of shared content of the user for a specified data range measured from receiving the customer support ticket.

12 . The computer system of claim 8 , wherein the sentiment analysis determines a sentiment of the user toward a topic associated with the customer support ticket, and an emotional status of the user at a time of submitting the customer support ticket.

13 . The computer system of claim 8 , wherein the personality analysis determines a personality of the user, including a patience level of the user, a technical skill level of the user, and a communication style of the user.

14 . The computer system of claim 8 , wherein one or more data science prediction algorithms are used to analyze a plurality of sentiment inputs resulting from the sentiment analysis and a plurality of personality inputs resulting from the personality analysis to determine a weight of the weighting scheme to be applied to the user sentiment score and the user personality score, further wherein the weight is based on an impact on a severity of the customer support ticket.

15 . A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, the computer readable program code comprising an algorithm that when executed by a computer processor of a computing system implements a method for prioritizing a customer support ticket system, the method comprising:
receiving, by a processor of a computing system, a customer support ticket from a user, wherein a default severity level associated with the customer support ticket is assigned; calculating, by the processor, a user sentiment score and a user personality score by applying a sentiment analysis and a personality analysis to use

Assignees

• IBM

Inventors

• Higgins Chunhui Y
• Ran Chuan
• Sassano Camillo
• Schipon Nancy A
• Zhang Bo

Classifications

• H04L41/5074 Primary

  Handling of user complaints or trouble tickets · CPC title

• G06Q10/06313 Primary

  Resource planning in a project environment · CPC title

• G06Q30/016

  After-sales · CPC title

• H04L41/5022

  by giving priorities, e.g. assigning classes of service · CPC title

• G10L25/63

  for estimating an emotional state · CPC title