Utilizing machine learning with call histories to determine support queue positions for support calls

• US 10,477,025 B1
• Filed: 12/20/2018
• Issued: 11/12/2019
• Est. Priority Date: 12/20/2018
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Edwards, Joshua, Benkreira, Abdelkadar M'Hamed, Mossoba, Michael, Colevas, Alexandra
• Primary Examiner(s): Hong, Harry S
• Application Number:
  US16/227,997
• Time in Patent Office: 327 Days
• Field of Search: 37926601-26603
• CPC Class Codes: G06Q 30/01 Customer relationship services
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: H04M 2203/551 Call history
• CPC Class Codes: H04M 2203/6045 Identity confirmation
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

A device receives, from a user device, a communication associated with a support issue encountered by a user of the user device and assigns the communication to a position in a support queue based on when the communication is received, wherein the support queue includes data identifying positions of other communications received from other users, and data identifying when the other communications were received. The device processes data identifying the communication and historical communication data describing prior communications associated with the user, with a model, to determine an average time spent on hold by the user for the prior communications. The device modifies the position of the communication in the support queue based on the average time and performs one or more actions based on modifying the position of the communication in the support queue.

Claims

1. A method, comprising:

receiving, by a device and from a user device, a communication associated with a support issue encountered by a user of the user device;

assigning, by the device, the communication to a position in a support queue based on when the communication is received,

wherein the support queue includes;

data identifying positions of other communications received from other users, and

data identifying when the other communications, received from the other users, were received;

processing, by the device, data identifying the communication, historical communication data describing prior communications associated with the user, and other communication data describing the other communications received from the other users, with a machine learning model, to determine different factors associated with the communication and respective weights for the different factors;

associating, by the device, the respective weights with the different factors;

generating, by the device, a score for the communication based on associating the respective weights with the different factors;

modifying, by the device, the position of the communication in the support queue based on the score for the communication and other scores for the other communications received from the other users; and

performing, by the device, one or more actions based on modifying the position of the communication in the support queue.

2. The method of claim 1, wherein performing the one or more actions includes one or more of:

providing data indicating that the position of the communication in the support queue improved;

processing the communication of the user based on modifying the position of the communication;

requesting, from the user device, verification of an identity of the user;

or

disconnecting the communication with the user device when the support issue is resolved.

3. The method of claim 1, wherein performing the one or more actions includes one or more of:

providing, to the user device, data identifying movement in the support queue for the position of the communication of the user;

causing another device to reboot or execute a self-diagnostic action;

or

causing the device to attempt to communicate with or attempt to repair the other device.

4. The method of claim 1, wherein performing the one or more actions comprises:

processing the communication based on modifying the position of the communication in the support queue.

5. The method of claim 1, wherein the historical communication data indicates that the prior communications required the user to wait on hold for a time period, and modifying the position of the communication in the support queue comprises:

modifying the position of the communication in the support queue based on the time period.

6. The method of claim 1, wherein the historical communication data indicates that at least one of the prior communications is associated with the support issue, and modifying the position of the communication in the support queue comprises:

assigning the communication to a top position in the support queue.

7. The method of claim 1, wherein the data identifying the communication and the historical communication data include:

an identifier that identifies the user.

8. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to;

receive, from a user device, a communication associated with a support issue encountered by a user of the user device;

assign the communication to a position in a support queue based on when the communication is received,

wherein the support queue includes;

data identifying positions of other communications received from other users, and

data identifying when the other communications, received from the other users, were received;

process data identifying the communication, historical communication data describing prior communications associated with the user, and other communication data describing the other communications received from the other users, with a machine learning model, to determine different factors associated with the communication and respective weights for the different factors;

associate the respective weights with the different factors;

generate a score for the communication based on associating the respective weights with the different factors;

assign the communication to a different position in the support queue based on the score for the communication; and

perform one or more actions based on assigning the communication to the different position in the support queue.

9. The device of claim 8, wherein the one or more processors, when performing the one or more actions, are to one or more of:

provide data indicating that the different position of the communication in the support queue is improved relative to the position in the support queue;

process the communication of the user based on assigning the communication to the different position in the support queue;

disconnect the communication with the user device when the support issue is resolved;

cause an autonomous vehicle to travel to a location of the user;

or

cause an unmanned aerial vehicle to travel to the location of the user.

10. The device of claim 8, wherein the one or more processors, when performing the one or more actions, are to one or more of:

cause a particular device to reboot;

cause the particular device to execute a self-diagnostic action;

attempt to communicate with the particular device;

or

attempt to repair the particular device.

11. The device of claim 8, wherein the one or more processors are further to:

provide, to the user device, data identifying movement in the support queue for the communication; and

provide, to the user device, data indicating points awarded to the user based on the movement in the support queue for the communication.

12. The device of claim 8, wherein the one or more processors are further to:

receive, from the user device, a second communication associated with a second support issue encountered by the user of the user device;

determine an average time spent on hold by the user for the prior communications based the historical communication data describing the prior communications; and

assign the second communication to a second position in the support queue based on the average time.

13. The device of claim 8, wherein the historical communication data indicates that at least one of the prior communications is associated with the support issue, and the one or more processors, when assigning the communication to the different position in the support queue, are to:

assign the communication to a top position in the support queue.

14. The device of claim 8, wherein the other communication data indicates that a particular communication, of at least one of the other communications received from the other users, is associated with a problem user, and the one or more processors, when modifying the position of the communication in the support queue, are to:

assign the communication to better position in the support queue than a second position to which the particular communication is assigned.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to;

receive, from a user device, a communication associated with a support issue encountered by a user of the user device;

assign the communication to a position in a support queue based on when the communication is received,

wherein the support queue includes;

data identifying positions of other communications received from other users, and

data identifying when the other communications, received from the other users, were received;

process data identifying the communication, historical communication data describing prior communications associated with the user, and other communication data describing the other communications received from the other users, with a machine learning model, to determine different factors associated with the communication and respective weights for the different factors;

associate the respective weights with the different factors;

generate a score for the communication based on associating the respective weights with the different factors;

modify the position of the communication in the support queue based on the score for the communication; and

perform one or more actions based on modifying the position of the communication in the support queue.

16. The non-transitory computer-readable medium of claim 15, wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

receive, from the user device, a second communication associated with a second support issue encountered by the user of the user device;

assign the second communication to a second position in the support queue based on when the second communication is received;

process data identifying the second communication, the historical communication data, and the other communication data describing the other communications received from the other users, with the machine learning model, to determine second factors associated with the second communication and respective second weights for the second factors;

associate the respective second weights with the second factors;

generate a second score for the second communication based on associating the respective second weights with the second factors; and

modify the second position of the second communication in the support queue based on the second score for the second communication.

17. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to one or more of:

provide data indicating that the position of the communication in the support queue improved;

process the communication based on modifying the position of the communication;

or

disconnect the communication when the support issue is resolved.

18. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to one or more of:

cause a particular device to reboot;

cause the particular device to execute a self-diagnostic action;

attempt to communicate with the particular device;

or

attempt to repair the particular device.

19. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to at least:

process the communication based on modifying the position of the communication in the support queue.

20. The non-transitory computer-readable medium of claim 15, wherein the data identifying the communication and the historical communication data include:

an identifier that identifies the user.