Shadow queue for callers in a performance/pattern matching based call routing system

• US 8,644,490 B2
• Filed: 08/29/2008
• Issued: 02/04/2014
• Est. Priority Date: 08/29/2008
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Satmap International Holdings, Ltd.
• Inventors: Stewart, Randall R.
• Primary Examiner(s): ADDY, THJUAN KNOWLIN
• Application Number:
  US12/202,101
• Publication Number:
  US 20100054453A1
• Time in Patent Office: 1,985 Days
• Field of Search: 37926501-26502, 37926511-26512, 379/266.02, 379/265.05, 379/266.01
• US Class Current: 379/265.12
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

Methods and systems are disclosed for routing callers to agents in a contact center, along with an intelligent routing system. A method for routing callers includes routing a caller, if agents are available, to an agent based on a pattern matching algorithm (which may include performance based matching, pattern matching based on agent and caller data, computer models for predicting outcomes of agent-caller pairs, and so on). Further, if no agents are available for the incoming caller, the method includes holding the caller in a shadow queue, e.g., a set of callers. When an agent becomes available the method includes scanning all of the callers in the shadow queue and matching the agent to the best matching caller within shadow queue.

Claims

1. A method for routing calls in a call routing center environment, the method comprising the acts performed on one or more computers of:

determining a skill set for a caller;

if agents are available for the determined skill set;

determining, using a pattern matching algorithm, a predicted chance of a desired interaction between the caller and two or more available agents; and

routing the caller an agent having a higher predicted chance of the desired interaction; and

if no agents are available for the determined skill set;

holding the caller in a set of callers;

when an agent becomes available, determining, using the pattern matching algorithm, a predicted chance of the desired interaction between the agent that became available and two or more callers within the set of callers; and

routing a caller having a higher predicted chance of the desired interaction to the agent that became available.

2. The method of claim 1, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises comparing caller data for the caller to agent data for each of the available agents via the pattern matching algorithm.

3. The method of claim 1, wherein determining using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises comparing agent data for the agent that became available to caller data for each of the set of callers via the pattern matching algorithm.

4. The method of claim 1, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises using a computer model reflecting the predicted chances of the desired interaction for the caller and each available agent.

5. The method of claim 1, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises using a computer model reflecting the predicted chances of the desired interaction for the agent that became available and each of the set of callers.

6. The method of claim 1, wherein the set of callers includes a plurality of callers.

7. The method of claim 1, further comprising:

if the caller is held for too long moving the caller to a skill set queue, which is matched with the next available agent.

8. The method of claim 1, wherein the caller is not routed from the set of callers based on a queue order.

9. A method for routing calls in a call routing center environment, the method comprising the acts performed on one or more computers of:

if agents are available;

determining, using a pattern matching algorithm, a predicted chance of a desired interaction between a caller and two or more available agents; and

causing the caller to be routed to an agent having a higher predicted chance of the desired interaction; and

if no agents are available;

holding the caller in a set of callers;

when an agent becomes available, determining, using the pattern matching algorithm, a predicted chance of the desired interaction between the agent that became available and two or more callers within the set of callers; and

causing a caller having a higher predicted change of the desired interaction to be routed to the agent that became available.

10. The method of claim 9, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises comparing caller data for the caller to agent data for each of the available agents via the pattern matching algorithm.

11. The method of claim 9, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises comparing agent data for the agent that became available to caller data for each of the set of callers via the pattern matching algorithm.

12. The method of claim 9, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises using a computer model reflecting the predicted chances of the desired interaction for the caller and each available agent.

13. The method of claim 9, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises using a computer model reflecting the predicted chances of the desired interaction for the agent that became available and each of the set of callers.

14. The method of claim 9, further comprising:

if the caller is held for too long adding the caller to a queue, which operates to match the caller with the next available agent based on queue order.

15. Apparatus for routing callers to agents in a call routing center environment, the apparatus comprising one or more computers configured with:

logic for determining if agents are available for a caller;

logic for determining, if agents are available, a predicted chance of a desired interaction between the caller and two or more available agents;

logic for causing the caller to be routed, if agents are available, to the agent having a higher predicted chance of the desired interaction; and

logic for holding the caller in a set of callers, if no agents are available, and when an agent becomes available, determining a predicted chance of the desired interaction between the agent that became available and two or more callers within the set of callers and matching the agent that became available to the caller having a higher predicted chance of the desired interaction.

16. The apparatus of claim 15, further comprising logic for determining a skill set of the caller.

17. The apparatus of claim 15, wherein determining, if agents are available, the predicted chance of the desired interaction between the caller and the two or more available agents comprises comparing caller data for the caller to agent data for each of the available agents via a pattern matching algorithm.

18. The apparatus of claim 15, wherein determining the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises comparing agent data for the agent that became available to caller data for each of the set of callers via a pattern matching algorithm.

19. The apparatus of claim 15, wherein determining, if agents are available, the predicted chance of the desired interaction between the caller and the two or more available agents comprises using a computer model reflecting the predicted chances of the desired interaction for the caller and each available agent.

20. The apparatus of claim 15, wherein determining the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises using a computer model reflecting the predicted chances of the desired interaction for the agent that became available and each of the set of callers, and wherein matching the agent that became available to the caller having the higher predicted chance of the desired interaction comprises routing the caller having the highest predicted chance of the desired interaction to the agent that became available.

21. The apparatus of claim 15, further comprising logic operable to move the caller to a queue that is matched with the next available agent if the caller is held for a predetermined amount of time.

22. A non-transitory computer readable storage medium comprising computer readable instructions for carrying out a method comprising the acts of:

if agents are available;

determining, using a pattern matching algorithm, a predicted chance of a desired interaction between the caller and two or more available agents; and

causing the caller to be routed to an agent having a higher predicted chance of the desired interaction; and

if no agents are available;

holding the caller in a set of callers;

when an agent becomes available, determining, using the pattern matching algorithm, a predicted chance of the desired interaction between the agent that became available and two or more callers within the set of callers; and

matching the agent that became available to the caller having the highest predicted chance of the desired interaction.

23. The non-transitory computer readable storage medium of claim 22, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises comparing caller data for the caller to agent data for each of the available agents via the pattern matching algorithm.

24. The non-transitory computer readable storage medium of claim 22, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises comparing agent data for the agent that became available to caller data for each of the set of callers via the pattern matching algorithm.

25. The non-transitory computer readable storage medium of claim 22, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the caller and the two or more available agents comprises using a computer model reflecting the predicted chances of the desired interaction for the caller and each available agent.

26. The non-transitory computer readable storage medium of claim 22, wherein determining, using the pattern matching algorithm, the predicted chance of the desired interaction between the agent that became available and the two or more callers within the set of callers comprises using a computer model reflecting the predicted chances of the desired interaction for the agent that became available and each of the set of callers.