IP Library Granted Patent US 9,894,205
Granted Patent B1
US 9,894,205 · App. 14/494,041 · Granted Feb 13, 2018

Measuring contact center agent effectiveness using a predictive model

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 9,894,205
App. No.
14/494,041
Granted
Feb 13, 2018
Kind
B1
Abstract

An agent's performance is measured using a predictive model calculating an expected probability of success for each outbound communication, such as a call, handled by the agent that has reached the desired (“right”) party. An agent's cumulative actual performance value is maintained based on each “successful” contact, as indicated by a disposition code provided by the agent. A cumulative expected probability value of a “successful” communication is also maintained based on each call that reaches the right party where the expected probability of a “successful” call is determined by the predictive model. The agent's performance value can be determined by comparing the cumulative actual performance value with the cumulative expected probability of success value. The agent's performance value can then be compared to the performance value of other agents to identify agents performing above-expectations or below-expectations.

Claims (52)

1. A method for determining a performance value indicating performance of an agent in a contact center handling outbound calls, comprising:

developing a predictive model configured to indicate an expected likelihood of a successful outcome of the agent interacting with a respective account holder represented by a contact in a dialing list;

initiating an outbound call for each of a plurality of contacts in the dialing list by a call handler, wherein upon the outbound call resulting in a right party connect in which the respective account holder interacts with the agent:

determining the expected likelihood of the successful outcome by a predictive module platform system using the predictive model for the outbound call;

incrementing a cumulative expected success value for the agent by the predictive module platform system adding the expected likelihood of the successful outcome to the cumulative expected success value;

receiving a call disposition code at the call handler indicated by the agent for the outbound call, the call disposition code indicating whether the successful outcome occurred from the agent interacting with the respective account holder; and

incrementing a cumulative actual success value for the agent by the predictive module platform system adding a predetermined value to the cumulative actual success value upon the call disposition code indicating the successful outcome occurred;

ascertaining the performance value for the agent by comparing the cumulative actual success value with the cumulative expected success value;

ranking the performance value of the agent among a plurality of performance values associated with a plurality of agents;

identifying the agent as a top performer with respect to the plurality of agents based on the ranking of the performance value of the agent; and

in response to identifying the agent as a top performer:

identifying a plurality of outbound calls handled by the agent in which the expected likelihood of the successful outcome for each of the calls in the plurality of outbound calls was below a threshold value and the disposition code for each of the calls in the plurality of outbound calls indicated the successful outcome occurred; and

performing speech analytics on the plurality of outbound calls by a speech analytics system to identify one or more common characteristics within the plurality of outbound calls reflective of one or more skills of the agent in handling the plurality of outbound calls.

2. The method of claim 1 , wherein the outbound call for each of the plurality of contacts in the dialing list is a debt-collection call type and the expected likelihood of the successful outcome is an expected likelihood of the respective account holder providing a promise-to-pay to the agent as determined by the predictive model.

3. The method of claim 2 , where the call disposition code provided to the call handler reflects whether the respective account holder provided a promise to make a payment on a debt.

4. The method of claim 1 , wherein comparing the cumulative actual success value with the cumulative expected success value involves computing a ratio of the cumulative actual success value to the cumulative expected success value.

5. The method of claim 1 , wherein the performance value is expressed as a percentage value in which if the percentage value exceeds 100%, then the performance value indicates the agent is performing above expectations.

6. A non-transitory computer readable medium storing instructions that when executed cause one or more processors to:

based upon an outbound call initiated for an agent in a contact center for each of a plurality of contacts in a dialing list resulting in a right party answering who interacts with the agent:

determine an expected likelihood of a successful outcome by using a predictive model for the outbound call;

increment a cumulative expected success value for the agent by adding the expected likelihood of the successful outcome to the cumulative expected success value;

receive an indication on whether the successful outcome occurred from the agent interacting with the right party; and

increment a cumulative actual success value for the agent by adding a predetermined value to the cumulative actual success value upon the indication identifying the successful outcome occurred;

ascertain a performance value for the agent by comparing the cumulative actual success value with the cumulative expected success value;

rank the performance value of the agent among a plurality of performance values associated with a plurality of agents;

identify the agent as a top performer with respect to the plurality of agents based on the ranking of the performance value of the agent; and

in response to identifying the agent as a top performer:

identify a plurality of outbound calls handled by the agent in which the expected likelihood of the successful outcome for each of the calls in the plurality of outbound calls was below a threshold value and the indication for each of the calls in the plurality of outbound calls identifying the successful outcome occurred; and

perform speech analytics on the plurality of outbound calls to identify one or more common characteristics within the plurality of outbound calls reflective of one or more skills of the agent in handling the plurality of outbound calls.

7. The non-transitory computer readable medium of claim 6 , wherein the indication reflects whether a promise-to-pay was provided from the right party.

8. The non-transitory computer readable medium of claim 6 , wherein comparing the cumulative actual success value with the cumulative expected success value involves computing a ratio of the cumulative actual success value to the cumulative expected success value.

9. A system for determining a performance value indicating performance of an agent in a contact center handling outbound calls, the system comprising at least one processor configured to:

based upon an outbound call initiated for each of a plurality of contacts in a dialing list resulting in a right party answering who interacts with the agent:

determine an expected likelihood of a successful outcome by using a predictive model for the outbound call;

increment a cumulative expected success value for the agent by adding the respective expected likelihood of the successful outcome to the cumulative expected success value;

receive an indication on whether the successful outcome occurred from the agent interacting with the right party; and

increment a cumulative actual success value for the agent by adding a predetermined value to the cumulative actual success value; and

ascertain the performance value for the agent by comparing the cumulative actual success value with the cumulative expected success value;

rank the performance value of the agent among a plurality of performance values associated with a plurality of agents;

identify the agent as a top performer with respect to the plurality of agents based on the ranking of the performance value of the agent; and

in response to identifying the agent as a top performer:

identify a plurality of outbound calls handled by the agent in which the expected likelihood of the successful outcome for each of the calls in the plurality of outbound calls was below a threshold value and the indication for each of the calls in the plurality of outbound calls identifying the successful outcome occurred; and

perform speech analytics on the plurality of outbound calls to identify one or more common characteristics within the plurality of outbound calls reflective of one or more skills of the agent in handling the plurality of outbound calls.

10. The system of claim 9 , wherein the at least one processor is further configured to:

develop the predictive model configured to provide the expected likelihood of the successful outcome.

11. The system of claim 9 , wherein the at least one processor is further configured to:

generate a performance ranking report comprising a ranking of the agent along with the plurality of agents.

12. The system of claim 9 , wherein comparing the cumulative actual success value with the cumulative expected success value by the processor involves the processor computing a ratio of the cumulative actual success value to the cumulative expected success value.

13. The system of claim 9 , wherein the indication reflects whether the right party committed to making a payment on a debt to the agent.

14. The method of claim 1 , wherein the one or more common characteristics comprise at least one of: a percentage of the plurality of outbound calls measured by at least one of time and word count in which the respective account holder is speaking versus the agent; a relative dialogue format between the respective account holder and the agent for the plurality of outbound calls; a relative emotional index of speech used by the agent during various portions of the plurality of outbound calls; and how long and how often the agent places the respective account holder on hold during the plurality of outbound calls.

15. The non-transitory computer readable medium of claim 6 , wherein the one or more common characteristics comprise at least one of: a percentage of the plurality of outbound calls measured by at least one of time and word count in which the right party is speaking versus the agent; a relative dialogue format between the right party and the agent for the plurality of outbound calls; a relative emotional index of speech used by the agent during various portions of the plurality of outbound calls; and how long and how often the agent places the right party on hold during the plurality of outbound calls.

16. The system of claim 9 , wherein the one or more common characteristics comprise at least one of: a percentage of the plurality of outbound calls measured by at least one of time and word count in which the right party is speaking versus the agent; a relative dialogue format between the right party and the agent for the plurality of outbound calls; a relative emotional index of speech used by the agent during various portions of the plurality of outbound calls; and how long and how often the agent places the right party on hold during the plurality of outbound calls.

Assignments (12)
RELEASE OF SECURITY INTEREST Recorded Oct 27, 2025
From: JEFFERIES FINANCE LLC, AS COLLATERAL AGENT
To: ALVARIA CAYMAN (WEM); ALVARIA CAYMAN (CXIP)
Reel/Frame 073360/0209 →
ASSIGNMENT Recorded Oct 27, 2025
From: ALVARIA CAYMAN (WEM); ALVARIA CAYMAN (CXIP); NOBLE SYSTEMS, LLC
To: ALVARIA, INC.
Reel/Frame 073360/0481 →
SECURITY INTEREST Recorded Oct 27, 2025
From: ALVARIA, INC.
To: JEFFERIES FINANCE LLC, AS COLLATERAL AGENT
Reel/Frame 073360/0564 →
RELEASE OF SECURITY INTEREST Recorded Mar 20, 2024
From: JEFFRIES FINANCE LLC
To: ALVARIA, INC.; NOBLE SYSTEMS, LLC
Reel/Frame 066850/0428 →
PATENT SECURITY AGREEMENT Recorded Mar 20, 2024
From: ALVARIA CAYMAN (WEM); ALVARIA CAYMAN (CXIP)
To: JEFFERIES FINANCE LLC
Reel/Frame 066850/0334 →
RELEASE OF SECURITY INTEREST Recorded Mar 20, 2024
From: JEFFRIES FINANCE LLC
To: ALVARIA, INC.; NOBLE SYSTEMS, LLC
Reel/Frame 066850/0384 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 20, 2024
From: NOBLE SYSTEMS, LLC
To: ALVARIA CAYMAN (CX)
Reel/Frame 066850/0556 →
CERTIFICATE OF CONVERSION Recorded Mar 12, 2024
From: NOBLE SYSTEMS CORPORATION, A GEORGIA CORPORATION
To: NOBLE SYSTEMS, LLC, A DELAWARE LIMITED LIABILITY COMPANY
Reel/Frame 066794/0435 →
RELEASE OF SECURITY INTEREST Recorded May 10, 2021
From: WELLS FARGO CAPITAL FINANCE, LLC
To: NOBLE SYSTEMS CORPORATION
Reel/Frame 056193/0363 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded May 6, 2021
From: NOBLE SYSTEMS CORPORATION; ASPECT SOFTWARE, INC.
To: JEFFERIES FINANCE LLC
Reel/Frame 057261/0093 →
SECOND LIEN PATENT SECURITY AGREEMENT Recorded May 6, 2021
From: NOBLE SYSTEMS CORPORATION; ASPECT SOFTWARE, INC.
To: JEFFERIES FINANCE LLC
Reel/Frame 057674/0664 →
AMENDMENT Recorded Jun 2, 2015
From: NOBLE SYSTEMS CORPORATION
To: WELLS FARGO CAPITAL FINANCE, LLC
Reel/Frame 035812/0507 →