Separate pattern matching algorithms and computer models based on available caller data
View Patent ↗Apparatus and methods are disclosed for routing callers to agents in a contact center. Exemplary methods and system include using one of a plurality of different computer models for matching callers to agents, the model selected based on a degree and/or type of caller data available. The models may include queue routing, performance based matching, adaptive pattern matching algorithms, or other computer models for matching callers to agents. In one example, similar adaptive models may be used for two or more different degrees/types of caller data, but are trained differently, e.g., based on the degree/type of caller data. Different models for routing callers to agents may perform differently for different degrees/types of caller data. Further, training correlation or adaptive pattern matching algorithms based on different degrees/types of caller data may improve their respective performance compared to a single algorithm for all degrees/types of caller data.
1. A method for routing callers to agents in a call-center routing environment, the method comprising the acts of:
receiving or determining, by one or more computers, caller data associated with an incoming caller;
determining or receiving, by the one or more computers, either a type or a degree or both the type and the degree, of the caller data associated with the caller, wherein a respective degree comprises a respective portion of a set of caller data types;
selecting, by the one or more computers, an algorithm from at least two different algorithms for matching the caller to an agent, wherein at least one of the at least two different algorithms comprises an adaptive correlation algorithm trained on past caller data and/or agent data for agent-caller pairs matched according to the adaptive correlation algorithm, wherein the one or more computers select the algorithm based on either the type or the degree of the caller data associated with the caller that was determined or received, or based on both the type and the degree of the caller data associated with the caller that were determined or received; and
causing, by the one or more computers, the caller to be routed based at least in part on results obtained from using the selected algorithm.
2. The method of claim 1 , further comprising selecting the algorithm based on one or both of a degree and type of agent data associated with the agent.
3. The method of claim 1 , wherein the caller is routed to an agent, a pool of callers, or a queue of callers.
4. The method of claim 1 , wherein the agent is matched to one of a plurality of callers via the selected algorithm.
5. The method of claim 1 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, and each of the adaptive correlation algorithms is trained using different degrees or types of caller data.
6. The method of claim 5 , wherein at least two of the adaptive correlation algorithms are trained on past caller data and agent data for agent-caller pairs matched according to the adaptive correlation algorithm.
7. The method of claim 5 , wherein at least one of the two adaptive correlation algorithms comprises a neural network algorithm.
8. The method of claim 1 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, with the adaptive correlation algorithms being different from each other.
9. The method of claim 1 , wherein one of the at least two algorithms comprises a performance based matching algorithm.
10. The method of claim 1 , wherein at least one of the at least two algorithms does not comprise an adaptive correlation algorithm.
11. The method of claim 1 , further comprising estimating an additional caller data based on the received or determined caller data.
12. The method of claim 1 , wherein a first degree of caller data comprises no caller data and a second degree of caller data comprises a portion of a predefined set of caller data.
13. The method of claim 1 , wherein the degree of caller data includes one or more of no caller data and Billing Telephone Number (BTN) data.
14. The method of claim 1 , wherein a type of caller data includes one or more types of Billing Telephone Number (BTN) data.
15. A system for routing callers to agents in a call center routing environment, the system comprising one or more computers configured with logic to:
receive or determine, by the one or more computers, caller data associated with an incoming caller;
determine or receive, by the one or more computers, either a type or a degree or both the type and the degree, of the caller data associated with the caller, wherein a respective degree comprises a respective portion of a set of caller data types;
select, by the one or more computers, an algorithm from at least two different algorithms for matching the caller to an agent, wherein at least one of the at least two different algorithms comprises an adaptive correlation algorithm trained on past caller data and/or agent data for agent-caller pairs matched according to the adaptive correlation algorithm, wherein the one or more computers select the algorithm based on either the type or the degree of the caller data associated with the caller that was determined or received, or based on both the type and the degree of the caller data associated with the caller that were determined or received; and
cause, by the one or more computers, the caller to be routed based at least in part on results obtained from using the selected algorithm.
16. The system of claim 15 , further comprising logic configured to select the algorithm based on one or both of a degree and type of agent data associated with the agent.
17. The system of claim 15 , wherein the caller is routed to an agent, a pool of callers, or a queue of callers.
18. The system of claim 15 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, and each of the adaptive correlation algorithms is trained using different degrees or types of caller data.
19. The system of claim 18 , wherein at least two of the adaptive correlation algorithms are trained on past caller data and agent data for agent-caller pairs matched according to the adaptive correlation algorithm.
20. The system of claim 18 , wherein at least one of the two adaptive correlation algorithms comprises a neural network algorithm.
21. The system of claim 15 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, with the adaptive correlation algorithms being different from each other.
22. The system of claim 15 , wherein one of the at least two algorithms comprises a performance based matching.
23. The system of claim 15 , wherein at least one of the at least two algorithms does not comprise an adaptive correlation algorithm.
24. The system of claim 15 , further comprising logic configured to estimate an additional caller data based on the received or determined caller data.
25. The system of claim 15 , wherein a first degree of caller data comprises no caller data and a second degree of caller data comprises a portion of a predefined set of caller data.
26. The system of claim 15 , wherein the degree of caller data includes one or more of no caller data and Billing Telephone Number (BTN) data.
27. The system of claim 15 , wherein the type of caller data includes one or more types of Billing Telephone Number (BTN) data.
28. A non-transitory computer readable storage medium comprising computer readable instructions for carrying out, when executed by one or more computers, the method of:
receiving or determining, by the one or more computers, caller data, associated with an incoming caller;
determining or receiving, by the one or more computers, either a type or a degree or both the type and the degree, of the caller data associated with the caller, wherein a respective degree comprises a respective portion of a set of caller data types;
selecting, by the one or more computers, an algorithm from at least two different algorithms for matching the caller to an agent, wherein at least one of the at least two different algorithms comprises an adaptive correlation algorithm trained on past caller data and/or agent data for agent-caller pairs matched according to the adaptive correlation algorithm, wherein the one or more computers select the algorithm based on either the type or the degree of the caller data associated with the caller that was determined or received, or based on both the type and the degree of the caller data associated with the caller that were determined or received; and
causing, by the one or more computers, the caller to be routed based at least in part on results obtained from using the selected algorithm.
29. The computer readable storage medium of claim 28 , further comprising program code for selecting the algorithm based on one or both of a degree and type of agent data associated with the agent.
30. The computer readable storage medium of claim 28 , wherein the caller is routed to an agent, a pool of callers, or a queue of callers.
31. The computer readable storage medium of claim 28 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, and each of the adaptive correlation algorithms is trained differently.
32. The computer readable storage medium of claim 31 , wherein at least two of the adaptive correlation algorithms are trained on past caller data and agent data for agent-caller pairs matched according to the adaptive correlation algorithm.
33. The computer readable storage medium of claim 31 , wherein at least one of the two adaptive correlation algorithms comprises a neural network algorithm.
34. The computer readable storage medium of claim 28 , wherein at least two of the at least two different algorithms each comprise an adaptive correlation algorithm, with the adaptive correlation algorithms being different from each other.
35. The computer readable storage medium of claim 28 , wherein one of the at least two algorithms comprises a performance based matching algorithm.
36. The computer readable storage medium of claim 28 , wherein at least one of the at least two algorithms does not comprise an adaptive correlation algorithm.
37. The computer readable storage medium of claim 28 , further comprising program code for estimating an additional caller data based on the received or determined caller data.
38. The computer readable storage medium of claim 28 , wherein a first degree of caller data comprises no caller data and a second degree of caller data comprises a portion of a predefined set of caller data.
39. The computer readable storage medium of claim 28 , wherein the degree of caller data includes one or more of no caller data and Billing Telephone Number (BTN) data.
40. The computer readable storage medium of claim 28 , wherein the type of caller data includes one or more types of Billing Telephone Number (BTN) data.