IP Library Granted Patent US 11,233,905
Granted Patent B1
US 11,233,905 · App. 16/791,769 · Granted Jan 25, 2022

Call center load balancing and routing management

Inventors: John Michael Lombard (Seattle, WA); Lambros Petropoulos (San Antonio, TX)
Assignee: United Services Automobile Association (USAA)
H04M3/5234H04M3/523H04M3/5175H04M3/5232H04M3/5237
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,233,905
App. No.
16/791,769
Granted
Jan 25, 2022
Kind
B1
Abstract

Systems and methods receiving performance data associated with a call center network; utilizing the performance data to create a model of the call center network; employing the model to run a simulation of the call center network that generates performance data associated with the model; using the model to generate solution parameters for the call center network; and providing the solution parameters to the call center network implementation in the call center network.

Claims (38)

1. A method, comprising:

receiving call center network performance data associated with a call center network;

utilizing the call center network performance data to create a model of the call center network;

employing the model to run a simulation of the call center network that generates model performance data associated with the model;

using the model to generate solution parameters for the call center network; and

automatically implementing the solution parameters in at least a portion of the call center network based on the model performance data exceeding the call center network performance data.

2. The method of claim 1 , further comprising:

comparing the call center network performance data to the model performance data; and

determining, based on the comparison, that the model performance data is outside of a predetermined level of similarity in relation to the call center network performance data.

3. The method of claim 2 , further comprising:

calibrating, based on determining that the model performance data is outside of the predetermined level, the model to the call center network, wherein calibrating is based on tuning one or more socially stochastic variables.

4. The method of claim 2 , wherein calibrating comprises:

changing a value of at least one parameter of the model until the call center network performance data and the model performance data are sufficiently similar.

5. The method of claim 4 , wherein sufficiently similar is when at least one metric in the call center network performance data is within a predetermined statistical deviation of a corresponding metric in the model performance data.

6. The method of claim 5 , wherein the metric comprises at least one of utilization rate, response time, abandonment rate, capture of high-propensity calls, and attribute matching.

7. The method of claim 2 , further comprising:

regenerating the model if the call center network performance data and the model performance data are not sufficiently similar.

8. The method of claim 1 , wherein the solution parameters are inputs to at least one of a load balancing algorithm or a routing algorithm.

9. The method of claim 1 , wherein employing the model comprises:

using the call center performance data to generate loading parameters for the model.

10. A system, comprising:

a call data module configured to receive call center performance data associated with a call center network;

a model execution module configured to create a model of the call center network and run a simulation of the call center network that generates model performance data associated with the model;

a solver module configured to create solution parameters for the call center network by using the model; and

an input/output module configured to implement the solution parameters in at least one call center network element based on the model performance data exceeding the call center performance data.

11. The system of 10 , wherein the model execution module is configured to:

calibrate the model to the call center network based on a determination that the call center performance data and the model performance data are outside a predetermined level of similarity.

12. The system of claim 11 , wherein calibrate the model comprises changing the value of at least one parameter of the model until the call center performance data and the model performance data are sufficiently similar.

13. The system of claim 12 , wherein sufficiently similar is when at least one metric in the call center performance data is within a predetermined statistical deviation of a corresponding metric in the model performance data.

14. The system of claim 13 , wherein the metric comprises at least one of utilization rate, response time, abandonment rate, capture of high-propensity calls, and attribute matching.

15. The system of claim 10 , wherein the model execution module regenerates the model if the call center network performance data and the model performance data are not sufficiently similar.

16. The system of claim 10 , wherein an architecture of the call center network utilizes two or more router types having two or more routing algorithms.

17. The system of claim 10 , comprising:

a load module configured to generate a plurality of simulated call loads to the model of the call center network, wherein the model execution module utilizes the load module to run the simulation.

18. The system of claim 10 , wherein the solution parameters are inputs to at least one of a load balancing algorithm or a routing algorithm.

19. The system of claim 10 , comprising:

a function module configured to generate one or more of a load balancing function, a routing function, and/or a penalty function for the model.

20. The system of claim 10 , wherein the model has a use time length, and wherein the model is calibrated upon expiration of the use time length.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 12, 2021
From: UIPCO, LLC
To: UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
Reel/Frame 057768/0411 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 17, 2020
From: LOMBARD, JOHN MICHAEL; PETROPOULOS, LAMBROS
To: UIPCO, LLC
Reel/Frame 051833/0201 →
Continuity (2)
Continuation In Part 16422138 · May 24, 2019
Continuation 15642635 · Jul 6, 2017
Cited By (1)
US 12,299,614