Systems and methods for routing callers to an agent in a contact center

• US 9,712,679 B2
• Filed: 01/28/2008
• Issued: 07/18/2017
• Est. Priority Date: 01/28/2008
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Afiniti International Holdings, Ltd.
• Inventors: Chishti, Zia, Spottiswoode, Stuart J., Jones, Christopher W.
• Primary Examiner(s): Jeanty, Romain
• Application Number:
  US12/021,251
• Publication Number:
  US 20090190740A1
• Time in Patent Office: 3,459 Days
• Field of Search: 705 713
• CPC Class Codes: H04M 2201/16 Sequence circuits
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2201/36 Memories
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04M 3/523 with call distribution or queueing
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 3/5235 Dependent on call type or called number [DNIS]
• CPC Class Codes: H04M 3/5236 Sequential or circular distribution
• CPC Class Codes: H04M 3/5238 with waiting time or load prediction arrangements

Abstract

Methods are disclosed for routing callers to agents in a contact center, along with an intelligent routing system. One or more agents are graded on achieving an optimal interaction, such as increasing revenue, decreasing cost, or increasing customer satisfaction. Callers are then preferentially routed to a graded agent to obtain an increased chance at obtaining a chosen optimal interaction. In a more advanced embodiment, caller and agent demographic and psychographic characteristics can also be determined and used in a pattern matching algorithm to preferentially route a caller with certain characteristics to an agent with certain characteristics to increase the chance of an optimal interaction.

Claims

1. A computer-implemented method for improving performance in a contact center system, the method comprising:

collecting, via at least one computer processor configured to operate in the contact center system, a plurality items of agent data for each agent in a set of agents comprising demographic data and/or psychographic data and agent grades;

collecting, via the at least one computer processor, at least one caller data for a caller comprising demographic data and/or psychographic data;

generating, via the at least one computer processor, a computer model reflecting predicted chances of an optimal interaction occurring between the caller and each of the agents in the set of agents using the agent data and the caller data;

matching and connecting, via the at least one computer processor, the caller to one of the agents based at least in part on the predicted chances of the optimal interaction from the computer model to increase the chance of an optimal interaction;

cycling, via the at least one computer processor, between using the computer model and a different algorithm to match and connect the caller to one of the agents;

generating, via the at least one computer processor, data for display on a visual computer interface screen measuring results of the matching and connecting using the computer model and results of the matching and connecting using the different algorithm; and

setting, via the at least one computer processor, times when the matching and connecting using the computer model is cycled on and when it is cycled off to provide a degree of randomness to achieve improved contact center system performance via agent learning.

2. The method of claim 1, wherein the agent data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

3. The method of claim 1, wherein the caller data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

4. The method of claim 1, wherein determining the caller data further comprises determining the caller'"'"'s CallerID.

5. The method of claim 1, further comprising connecting the caller to one of the agents with a minimally-acceptable predicted chance of an optimal interaction.

6. The method of claim 1, further comprising connecting the caller to one of the agents with the highest predicted chance of an optimal interaction.

7. The method of claim 1, further comprising determining an order of agent suitability for matches between the caller and at least two of the agents.

8. The method of claim 7, further comprising determining the availability of the agents, and connecting the caller to an available agent from the agents.

9. The method of claim 1, wherein the matches are partially randomized by a factor between about 0.1% and 99.9%.

10. The method of claim 1, wherein the computer model is generated via a pattern matching algorithm comprising one of a neural network algorithm or a genetic algorithm.

11. The method of claim 10, further comprising training the pattern matching algorithm by correlating the chance of an optimal interaction against the agent data and the caller data, wherein the agent data and the caller data are determined from at least one historical contact between a caller and an agent.

12. The method of claim 11, wherein training the pattern matching algorithm occurs periodically.

13. The method of claim 1, wherein the optimal interaction comprises one of improved revenue generation, decreased cost, or improved customer satisfaction.

14. The method of claim 1, further comprising weighting the optimal interaction against another optimal interaction, modifying the computer model to generate suitability scores for matches between the caller and each of the agents, and connecting the caller with one of the agents to increase the chance of the more heavily-weighted optimal interaction.

15. The method of claim 1, further comprising determining from an affinity database a caller affinity data for the caller, and using the caller affinity data to match the caller with at least one of the agents.

16. The method of claim 15, wherein the caller affinity data comprises one of purchase history, contact time history, or customer satisfaction history.

17. The method of claim 1, further comprising determining from an affinity database an agent affinity data for at least one of the agents, and using the agent affinity data to match the caller with at least one of the agents.

18. The computer-implemented method of claim 1, further comprising displaying the generated data on the visual computer interface screen.

19. An intelligent routing contact center system, the system comprising:

at least one computer processor configured to operate in the contact center system, wherein the at least one computer processor is further configured to;

collect a plurality items of agent data for each agent in a set of agents comprising demographic data and/or psychographic data and agent grades;

collect at least one caller data for a caller comprising demographic data and/or psychographic data;

generate a computer model reflecting predicted chances of an optimal interaction occurring between the caller and each of the agents in the set of agents using the agent data and the caller data;

match and connect the caller to one of the agents based at least in part on the predicted chances of the optimal interaction from the computer model to increase the chance of an optimal interaction;

cycle between using the computer model and a different algorithm to match and connect the caller to one of the agents;

generate data for display on a visual computer interface screen measuring results of the matching and connecting using the computer model and results of the matching and connecting using the different algorithm; and

set times when the matching and connecting using the computer model is cycled on and when it is cycled off to provide a degree of randomness to achieve improved contact center system performance via agent learning.

20. The system of claim 19, wherein the at least one computer processor is further configured to record one of an agent'"'"'s revenue generation performance or the agent'"'"'s contact time per caller.

21. The system of claim 19, further comprising a switching system.

22. The system of claim 19, further comprising a dialer.

23. The system of claim 19, further comprising a callerID device.

24. The system of claim 19, wherein the agent data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

25. The system of claim 24, wherein the caller data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

26. The system of claim 19, wherein the at least one computer processor is further configured to train a pattern matching algorithm that generates the computer model by correlating the chance of an optimal interaction against the agent data and the caller data, wherein the agent data and the caller data are determined from at least one historical contact between a caller and an agent.

27. The system of claim 19, wherein the at least one computer processor is further configured to weight the optimal interaction against another optimal interaction, modifying the computer model to generate suitability scores for matches between the caller and each of the two agents, and connecting the caller with one of the two agents to increase the chance of the more heavily-weighted optimal interaction.

28. The system of claim 19, wherein the at least one computer processor is further configured to display the generated data on the visual computer interface screen.

29. An article of manufacture for improving performance in a contact center system comprising:

a non-transitory computer processor readable medium; and

instructions stored on the medium;

wherein the instructions are configured to be readable from the medium by at least one computer processor configured to operate in the contact center system and thereby cause the at least one computer processor to operate so as to;

collect a plurality items of agent data for each agent in a set of agents comprising demographic data and/or psychographic data and agent grades;

collect at least one caller data for a caller comprising demographic data and/or psychographic data;

generate a computer model reflecting predicted chances of an optimal interaction occurring between the caller and each of the agents in the set of agents using the agent data and the caller data;

match and connect the caller to one of the agents based at least in part on the predicted chances of the optimal interaction from the computer model to increase the chance of an optimal interaction;

cycle between using the computer model and a different algorithm to match and connect the caller to one of the agents;

generate data for display on a visual computer interface screen measuring results of the matching and connecting using the computer model and results of the matching and connecting using the different algorithm; and

set times when the matching and connecting using the computer model is cycled on and when it is cycled off to provide a degree of randomness to achieve improved contact center system performance via agent learning.

30. The article of manufacture of claim 29, wherein the agent data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

31. The article of manufacture of claim 30, wherein the caller data comprises demographic data, wherein the demographic data comprises one of gender, race, age, education, accent, income, nationality, ethnicity, area code, zip code, marital status, job status, or credit score.

32. The article of manufacture of claim 29, wherein the at least one computer processor is further caused to operate so as to train a pattern matching algorithm that generates the computer model by correlating the chance of an optimal interaction against the agent data and the caller data, wherein the agent data and the caller data are determined from at least one historical contact between a caller and an agent.

33. The article of manufacture of claim 29, wherein the at least one computer processor is further caused to operate so as to weight the optimal interaction against another optimal interaction, modify the computer model to generate suitability scores for matches between the caller and each of the two agents, and connect the caller with one of the two agents to increase the chance of the more heavily-weighted optimal interaction.

34. The article of manufacture of claim 29, wherein the at least one computer processor is further caused to operate so as to display the generated data on the visual computer interface screen.