Call volume reduction based upon a propensity to call in connection with a reason code

Patent metadata

Field	Value
Publication number	US-10798242-B2
Application number	US-201916564943-A
Country	US
Kind code	B2
Filing date	Sep 9, 2019
Priority date	Dec 12, 2016
Publication date	Oct 6, 2020
Grant date	Oct 6, 2020

Abstract

Devices, computer-readable media and methods for delivering customer service content associated with a reason code are disclosed. Examples of the present disclosure may include a processor of a telecommunication network identifying a reason code associated with calls from customers to a customer call center and determining a set of shared traits among the customers. The shared traits may be based upon first network event data and first customer account data associated with the customers. The processor may further determine a customer with a propensity to call score that exceeds a threshold and with a customer profile that matches the set of shared traits. The customer profile may be based upon second network event data and second customer account data associated with the customer. The processor may further deliver a customer service content associated with the reason code to the customer via a communication modality that is determined for the customer.

First claim

What is claimed is:

1. A device deployed in a telecommunication service provider network, the device comprising:
a processor; and
a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
identifying a reason code associated with a plurality of calls from a plurality of customers to a customer call center;
determining a set of shared traits among the plurality of customers, wherein the set of shared traits is based upon first network event data and first customer account data associated with the plurality of customers;
determining a customer with a propensity to call score that exceeds a threshold score and with a customer profile that matches the set of shared traits, wherein the customer profile is based upon second network event data and second customer account data associated with the customer; and
delivering a customer service content associated with the reason code to the customer via a communication modality that is determined for the customer, in response to determining both that the propensity to call score exceeds the threshold score and that the customer profile matches the set of shared traits.

2. The device of claim 1 , wherein the set of shared traits is used in a binary classifier to determine whether the customer profile matches the set of shared traits.

3. The device of claim 2 , wherein the binary classifier comprises a support vector machine.

4. The device of claim 2 , wherein the determining the set of shared traits comprises:
training the binary classifier, wherein the first network event data and the first customer account data comprise training data for the binary classifier.

5. The device of claim 4 , wherein the determining the set of shared traits comprises:
testing the binary classifier, wherein the first network event data and the first customer account data further comprise testing data for the binary classifier.

6. The device of claim 1 , wherein the operations further comprise:
selecting the threshold score, wherein the threshold score is selected to achieve a target reduction of a number of calls to the customer call center associated with the reason code.

7. The device of claim 1 , wherein the propensity to call score of the customer is determined based upon a number of past calls of the customer to the customer call center and the customer profile.

8. The device of claim 1 , wherein the operations further comprise:
determining the communication modality for the customer, wherein the communication modality is determined based upon an effectiveness score for past presentations of a plurality of customer service contents to the customer via the communication modality.

9. The device of claim 8 , wherein the communication modality comprises:
an email;
a short message service message;
a multimedia messaging service message;
a social media post;
an automated voice message; or
a video message.

10. The device of claim 1 , wherein both the first network event data and the second network event data comprise:
call detail records;
trouble ticket system reports;
billing system reports;
provisioning system reports;
television viewing records; or
clickstream records.

11. The device of claim 1 , wherein both the first customer account data and the second customer account data comprise records storing customer characteristics of the customer that include at least one of:
a name;
an age;
an address;
subscription information;
identifications of customer devices;
a billing history;
a payment history; or
purchasing and ordering information.

12. The device of claim 1 , wherein records of the plurality of calls are tagged with the reason code by an interactive voice response system or a customer service agent of the customer call center.

13. A method comprising:
identifying, by a processor of a telecommunication service provider network, a reason code associated with a plurality of calls from a plurality of customers to a customer call center;
determining, by the processor, a set of shared traits among the plurality of customers, wherein the set of shared traits is based upon first network event data and first customer account data associated with the plurality of customers;
determining, by the processor, a customer with a propensity to call score that exceeds a threshold score and with a customer profile that matches the set of shared traits, wherein the customer profile is based upon second network event data and second customer account data associated with the customer; and
delivering, by the processor, a customer service content associated with the reason code to the customer via a communication modality that is determined for the customer, in response to determining both that the propensity to call score exceeds the threshold score and that the customer profile matches the set of shared traits.

14. The method of claim 13 , wherein the set of shared traits is used in a binary classifier to determine whether the customer profile matches the set of shared traits.

15. The method of claim 14 , wherein the binary classifier comprises a support vector machine.

16. The method of claim 14 , wherein the determining the set of shared traits comprises:
training the binary classifier, wherein the first network event data and the first customer account data comprise training data for the binary classifier.

17. The method of claim 16 , wherein the determining the set of shared traits further comprises:
testing the binary classifier, wherein the first network event data and the first customer account data further comprise testing data for the binary classifier.

18. The method of claim 13 , wherein the customer profile is generated by selecting the second network event data and the second customer account data to be included in the customer profile, wherein the second network event data and the second customer account data comprise customer traits that correspond to the set of shared traits.

19. The method of claim 13 , further comprising:
selecting the threshold score, wherein the threshold score is selected to achieve a target reduction of a number of calls to the customer call center associated with the reason code.

20. A non-transitory computer-readable storage medium storing instructions which, when executed by a processor of a telecommunication service provider network, cause the processor to perform operations, the operations comprising:
identifying a reason code associated with a plurality of calls from a plurality of customers to a customer call center;
determining a set of shared traits among the plurality of customers, wherein the set of shared traits is based upon first network event data and first customer account data associated with the plurality of customers;
determining a customer with a propensity to call score that exceeds a threshold score and with a customer profile that matches the set of shared traits, wherein the customer profile is based upon second network event data and second customer account data associated with the customer; and
delivering a customer service content associated with the reason code to the customer via a communication modality that is determined for the customer, in response to determining both that the propensity to call score exceeds the threshold score and that the customer profile matches the set of shared traits.

Assignees

• At & T Ip I Lp

Inventors

• Dunmire David
• Krishna Sanjay
• Green Don
• Roberts John
• Aspley Anna

Classifications

• H04M3/5158 Primary

  in combination with automated outdialling systems (devices for signalling identity of wanted subscriber H04M1/26) · CPC title

• H04M3/5183

  Call or contact centers with computer-telephony arrangements · CPC title

• H04M2203/555

  Statistics, e.g. about subscribers but not being call statistics · CPC title