Urgency-based queue management systems and methods

Patent metadata

Field	Value
Publication number	US-12293374-B2
Application number	US-202117509225-A
Country	US
Kind code	B2
Filing date	Oct 25, 2021
Priority date	Oct 25, 2021
Publication date	May 6, 2025
Grant date	May 6, 2025

Abstract

Disclosed embodiments may include a queue management system. The system may receive one or more utterances comprising a customer intent from a user device, determine a first queue from a plurality of queues in which to place the user based on the user intent, and receive first urgency data comprising battery indication data from the user device. The system may then determine, using a machine learning model, a first dynamic priority score for the user based on the user intent and the first urgency data including battery indication data associated with the user device. Based on the first dynamic priority score for the user, the system may assign an initial user-specific position within the first queue to the user that differs from a default initial position in the first queue. Based on updated urgency data, the system may dynamically update the user's position to a second user-specific position.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive, from a voice call initiated via a mobile application of a user device associated with a user, one or more utterances comprising a user intent;
determine a first queue from a plurality of queues in which to place the user based on the user intent;
receive first urgency data comprising battery indication data from the user device via the mobile application of the user device, the battery indication data being captured by the mobile application of the user device and comprising a battery level indication and an indication of whether the user device is charging;
determine, using a machine learning model, a first dynamic priority score for the user based on the user intent and the first urgency data, wherein the machine learning model is configured to not consider the battery level indication when determining a dynamic priority score when received urgency data provides an indication that the user device is charging;
assign an initial user-specific position within the first queue to the user based on the first dynamic priority score for the user, the initial user-specific position being different from a default initial position in the first queue; and
iteratively:
receive updated urgency data from the user device, wherein the updated urgency data is obtained by the mobile application of the user device in real time during the voice call;
determine, using the machine learning model, an updated dynamic priority score for the user based on the user intent and the updated urgency data;
determine whether to assign a new user-specific position within the first queue to the user based on the updated dynamic priority score; and
dynamically reassign one or more user positions in the first queue in response to determining to assign a new user-specific position within the first queue to the user based on the updated dynamic priority score.

2. The system of claim 1 , wherein the instructions are further configured to cause the system to:
detect a language associated with the one or more utterances; and
assign the user the first queue out of a plurality of queues based on the user intent and language.

3. The system of claim 1 , wherein the first urgency data further comprises location data.

4. The system of claim 1 , wherein the first urgency data further comprises recent account activity data.

5. The system of claim 1 , wherein the first urgency data further comprises location data, recent account activity data, time of day data, authorization data, or combinations thereof.

6. The system of claim 1 , wherein the instructions are further configured to cause the system to:
receive second urgency data from the user device;
determine, using the machine learning model, a second dynamic priority score for the user based on the user intent and the second urgency data; and
reassign the user a second user-specific position within the first queue based on the second dynamic priority score for the user.

7. The system of claim 6 , wherein the second urgency data comprises location data, battery indication data, recent account activity data, time of day data, authorization data, or combinations thereof.

8. The system of claim 1 , wherein the first urgency data further comprises one or more of an indication of whether the user device is roaming and an indication of whether the user device is accessing a wireless or cellular network.

9. A system, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive, from a voice call initiated via a mobile application of a user device associated with a user, one or more messages comprising a user intent;
determine a first queue from a plurality of queues in which to place the user based on the user intent;
receive first urgency data from the user device via the mobile application of the user device, the first urgency data being captured by the mobile application of the user device and comprising a battery level indication and an indication of whether the user device is charging;
determine, using a machine learning model, a first dynamic priority score for the user based on the user intent and the first urgency data, wherein the machine learning model is configured to not consider the battery level indication when determining a dynamic priority score when received urgency data provides an indication that the user device is charging;
assign an initial user-specific position within the first queue to the user based on the first dynamic priority score for the user, the initial user-specific position being different from a default initial position in the first queue; and
iteratively:
receive updated urgency data from the user device wherein the updated urgency data is obtained by the mobile application of the user device in real time during the voice call;
determine, using the machine learning model, an updated dynamic priority score for the user based on the user intent and the updated urgency data;
determine whether to assign a new user-specific position within the first queue to the user based on the updated dynamic priority score; and
dynamically reassign one or more user positions in the first queue in response to determining to assign a new user-specific position within the first queue to the user based on the updated dynamic priority score.

10. The system of claim 9 , wherein the instructions are further configured to cause the system to:
detect a language associated with the one or more messages; and
assign the user the first queue out of a plurality of queues based on the user intent and language.

11. The system of claim 9 , wherein the first urgency data comprises location data.

12. The system of claim 9 , wherein the first urgency data comprises battery indication data.

13. The system of claim 9 , wherein the first urgency data comprises recent account activity data.

14. The system of claim 13 , wherein the recent account activity data comprises a transaction indication and call indication within a predetermined time period.

15. The system of claim 9 , wherein the first urgency data comprises location data, battery indication data, recent account activity data, time of day data, authorization data, or combinations thereof.

16. The system of claim 9 , wherein the instructions are further configured to cause the system to:
receive second urgency data from the user device;
determine, using the machine learning model, a second dynamic priority score for the user based on the user intent and the second urgency data; and
reassign the user a second user-specific position within the first queue based on the second dynamic priority score for the user.

17. A method comprising:
receiving, from a voice call initiated via a mobile application of a user device associated with a user, one or more utterances or messages comprising a user intent;
determining a first queue from a plurality of queues in which to place the user based on the user intent;
receiving first urgency data from the user device via the mobile application of the user device, the first urgency data being captured by the mobile application of the user device and comprising a battery level indication and an indication of whether the user device is charging;
determining, using a machine learning model,

Assignees

• Capital One Services Llc

Inventors

• Lee Jonathan
• Moreau-Arnott Elijah
• Randall Garrett

Classifications

• G06Q10/06311

  Scheduling, planning or task assignment for a person or group · CPC title

• G06F40/263

  Language identification · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G07C2011/04

  related to queuing systems · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title