Separate matching models based on type of phone associated with a caller

• US 8,712,821 B2
• Filed: 12/09/2008
• Issued: 04/29/2014
• Est. Priority Date: 01/28/2008
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Satmap International Holdings, Ltd.
• Inventors: Spottiswoode, S. James P.
• Primary Examiner(s): Jeanty, Romain
• Application Number:
  US12/331,161
• Publication Number:
  US 20090190743A1
• Time in Patent Office: 1,967 Days
• Field of Search: 705/7.13, 705/7.29
• US Class Current: 705/7.29
• 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

Systems and methods are disclosed for routing callers to agents in a contact center. Exemplary methods and systems include using one of a plurality of different methods or computer models for matching callers to agents, the method or model selected based on a type of phone or phone number associated with a caller (e.g., residential, business, or mobile). The models may include queue routing, performance based matching, adaptive pattern matching algorithms, or the like. In one example, similar adaptive models may be used for two or more different types of phones, but trained differently, e.g., based on data and outcomes for the particular type of phone. Different models for routing callers to agents may perform differently for different types of phones. Further, training correlation or adaptive pattern matching algorithms based on different types of phones may improve performance compared to a single algorithm for all types of phones.

Claims

1. A method for routing incoming callers to agents in a call-center routing environment, the method comprising the acts of:

determining, by one or more computers, a type of phone associated with a caller, from among a plurality of types including a residential type and a business type;

selecting a measurement algorithm, by the one or more computers, from among at least a first measurement algorithm and a second measurement algorithm for matching a caller to an agent, wherein at least two of the measurement algorithms are pattern matching algorithms, wherein when the type of phone associated with the caller is determined, the respective measurement algorithm is selected based at least in part on the type of phone associated with the caller; and

matching, by the one or more computers, the caller to an agent based at least in part on the selected measurement algorithm,

wherein the at least two pattern matching algorithms are optimized for different output performances, and

wherein the output performance for at least one of the two pattern matching algorithms comprises at least one selected from the group of cost, revenue, sales, handle time, and customer satisfaction.

2. The method of claim 1, wherein the type of phone is determined from a phone number associated with the caller.

3. The method of claim 1, wherein the type of phone comprises one or more of a residential phone, mobile phone, or business phone.

4. The method of claim 1, wherein the type of phone is determined from Billing Telephone Number (BTN) data associated with the caller.

5. The method of claim 4, wherein the type of BTN data comprises one or more of residential phone number, mobile phone number, or business phone number.

6. The method of claim 4, wherein at least two of the at least two different measurement algorithms each comprise a pattern matching algorithm, and each of the pattern matching algorithms is trained differently.

7. The method of claim 6, wherein each of the pattern matching algorithms is trained on past caller data and agent data for agent-caller pairs matched according to the pattern matching algorithm.

8. The method of claim 6, wherein each of the pattern matching algorithms is trained on past caller data and agent data for a respective type of BTN data.

9. The method of claim 6, wherein at least one of the two pattern matching algorithms comprises a neural network algorithm.

10. The method of claim 1, wherein one of the measurement algorithms comprises a performance based matching algorithm.

11. The method of claim 1, wherein one of the measurement algorithms does not comprise a pattern matching algorithm.

12. The method of claim 1, further comprising estimating an additional caller data based on the determined caller data.

13. A system for routing callers to agents in a call center routing environment, comprising:

one or more computers with a memory configured with computer-readable program code, that when executed, causes performance by the one or more computers of the steps;

determining, by the one or more computers, a type of phone associated with a caller, from among a plurality of types including a residential type and a business type;

selecting a measurement algorithm, by the one or more computers, from among at least a first measurement algorithm and a second measurement algorithm for matching a caller to one of a plurality of agents, wherein at least two of the measurement algorithms are pattern matching algorithms, wherein when the type of phone associated with the caller is determined, the respective measurement algorithm is selected based at least in part on the type of phone associated with the caller; and

matching, by the one or more computers, the caller to an agent based at least in part on the selected measurement algorithm,

wherein the at least two pattern matching algorithms are optimized for different output performances, and

wherein the output performance for at least one of the two pattern matching algorithms comprises at least one selected from the group of cost, revenue, sales, handle time, and customer satisfaction.

14. The system of claim 13, wherein the type of phone is determined from a phone number associated with the caller.

15. The system of claim 13, wherein the type of phone comprises one or more of a residential phone, mobile phone, or business phone.

16. The system of claim 13, wherein the type of phone is determined from Billing Telephone Number (BTN) data associated with the caller.

17. The system of claim 16, wherein at least two of the at least two different measurement algorithms each comprise a pattern matching algorithm, and each of the pattern matching algorithms is trained differently.

18. The system of claim 17, wherein each of the pattern matching algorithms is trained on past caller data and agent data for agent-caller pairs matched according to the pattern matching algorithm.

19. The system of claim 17, wherein each of the pattern matching algorithms is trained on past caller data and agent data for a respective type of BTN data.

20. The system of claim 17, wherein at least one of the two pattern matching algorithms comprises a neural network algorithm.

21. The system of claim 13, wherein one of the measurement algorithms comprises a performance based matching algorithm.

22. The system of claim 13, wherein one of the measurement algorithms does not comprise a pattern matching algorithm.

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

determining, by one or more computers, a type of phone associated with a caller, from among a plurality of types including a residential type and a business type;

selecting a measurement algorithm, by the one or more computers, from among at least a first measurement algorithm and a second measurement algorithm for matching a caller to one of a plurality of agents, wherein at least two of the measurement algorithms are pattern matching algorithms, wherein when the type of phone associated with the caller is determined, the respective measurement algorithm is selected based at least in part on the type of phone associated with the caller; and

matching, by the one or more computers, the caller to an agent based at least in part on the selected measurement algorithm,

wherein the at least two pattern matching algorithms are optimized for different output performances, and

wherein the output performance for at least one of the two pattern matching algorithms comprises at least one selected from the group of cost, revenue, sales, handle time, and customer satisfaction.

24. The computer readable storage medium of claim 23, wherein the type of phone is determined from a phone number associated with the caller.

25. The computer readable storage medium of claim 23, wherein the type of phone comprises one or more of a residential phone, mobile phone, or business phone.

26. The computer readable storage medium of claim 23, wherein the type of phone is determined from Billing Telephone Number (BTN) data associated with the caller.

27. The computer readable storage medium of claim 26, wherein at least two of the at least two different measurement algorithms each comprise a pattern matching algorithm, and each of the pattern matching algorithms is trained differently.

28. The computer readable storage medium of claim 27, wherein each of the pattern matching algorithms is trained on past caller data and agent data for agent-caller pairs matched according to the pattern matching algorithm.

29. The computer readable storage medium of claim 27, wherein each of the pattern matching algorithms is trained on past caller data and agent data for a respective type of BTN data.

30. The computer readable storage medium of claim 27, wherein at least one of the two pattern matching algorithms comprises a neural network algorithm.

31. The computer readable storage medium of claim 23, wherein one of the measurement algorithms comprises a performance based matching algorithm.

32. The computer readable storage medium of claim 23, wherein one of the measurement algorithms does not comprise a pattern matching algorithm.