Systems and methods for selectively routing calls to a call center

• US 9,401,992 B2
• Filed: 07/17/2012
• Issued: 07/26/2016
• Est. Priority Date: 07/17/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Srinivas, Sharath, Hu, Bo, Koomen, Johannes A.
• Primary Examiner(s): Matar, Ahmad F
• Assistant Examiner(s): Intavong, Jirapon
• Application Number:
  US13/551,263
• Publication Number:
  US 20140023186A1
• Time in Patent Office: 1,470 Days
• Field of Search: 379/265.01, 379/265.02, 379/266.01, 379/266.03, 379/266.05, 379/266.08
• US Class Current: 1/1
• CPC Class Codes: H04M 2201/14 Delay circuits; Timers
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5231 with call back arrangements
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5238 with waiting time or load prediction arrangements

Abstract

Systems and methods of routing calls may include receiving a plurality of calls, and for each of the plurality of calls, determining a threshold time that may be a maximum service time for the call, estimating an expected service time for the call, comparing the threshold time with the expected service time for the call, and assigning the call into one of a plurality of queues based upon the comparing. The method of routing may further include prioritizing the plurality of queues based upon the expected service time for each call in each of the plurality of queues, directing each call in a first queue of the plurality of queues to a first group of agents, and providing a callback prompt to each call in a second queue of the plurality of queues, wherein a priority of the first queue is higher than a priority of the second queue.

Claims

1. A method of routing calls in a call center, comprising:

forecasting, by call activity forecaster, an anticipated call volume for each of a plurality of time intervals, wherein the forecasting is based upon historic call volume information;

receiving, by a communication port in the call center, a plurality of calls;

for each of the plurality of calls;

determining, by a threshold comparator, a threshold time as an indication of a maximum service time for the call, wherein the threshold time is based upon at least;

a first time interval during which the call was received,

the forecasted anticipated call volume for the first time interval,

a number of agents in each of a plurality of queues, the agents being assigned to answer incoming calls, and

average wait times in each of the plurality of queues;

estimating, by a duration estimator, an expected service time for the call,

comparing, by the threshold comparator, the threshold time with the expected service time for the call, and

assigning, by a router, the call into one of the plurality of queues based upon the comparing;

prioritizing, by the router, the plurality of queues based upon the expected service time for each call in each of the plurality of queues;

directing, by the router, each call in a first queue of the plurality of queues to a first group of agents, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises;

2. The method of claim 1, further comprising:

directing a second group of agents to place a return call to each caller that placed the call assigned to the second queue.

3. The method of claim 2, wherein directing the second group of agents to place the return call comprises determining a number of agents in the second group by a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

4. The method of claim 2, wherein directing the second group of agents to place the return call comprises determining a number of agents in the second group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

5. The method of claim 1, wherein estimating the expected service time further comprises:

using an interactive voice response system to obtain an input from a caller placing the call;

determining the nature of the call based upon the input;

comparing the nature of the call to a statistical database; and

based upon the comparing, estimating the expected service time for the call.

6. The method of claim 1, wherein determining the threshold time comprises using a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

7. The method of claim 1, wherein determining the threshold time comprises using a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

8. The method of claim 1, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, and an expected total service time for a plurality of calls received in the first time interval.

9. The method of claim 8, further comprising determining a number of agents in a second group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, a total volume of a plurality of calls received in the first time interval, and the number of agents in the first group.

10. The method of claim 1, wherein determining the threshold time further comprises confirming that each of the average wait times in each of the plurality of queues is less than or equal to a predetermined maximum wait time for each of the plurality of queues.

11. A method of routing calls in a call center, comprising:

forecasting, by call activity forecaster, an anticipated call volume for each of a plurality of time intervals, wherein the forecasting is based upon historic call volume information;

receiving, by a communication port in the call center, a plurality of calls;

for each of the plurality of calls;

determining, by a threshold comparator, a threshold time as an indication of a maximum service time for the call, wherein the threshold time is based upon at least;

a first time interval during which the call was received,

the forecasted anticipated call volume for the first time interval,

a number of agents in each of a plurality of queues, the agents being assigned to answer incoming calls, and

average wait times in each of the plurality of queues;

estimating, by a duration estimator, an expected service time for the call,

comparing, by the threshold comparator, the threshold time with the expected service time for the call, and

assigning, by a router, the call into one of the plurality of queues based upon the comparing;

prioritizing, by the router, the plurality of queues based upon the expected service time for each call in each of the plurality of queues;

directing, by the router, each call in a first queue of the plurality of queues to a first group of agents;

providing, by the communication port, a callback prompt to each call in a second queue of the plurality of queues, wherein a priority of the first queue is higher than a priority of the second queue; and

directing a second group of agents to place a return call to each caller that placed the call assigned to the second queue, wherein directing the second group of agents to place the return call comprises determining a number of agents in the second group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises;

12. The method of claim 11, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group by a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

13. The method of claim 11, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

14. The method of claim 11, wherein estimating the expected service time further comprises:

using an interactive voice response system to obtain an input from a caller placing the call;

determining the nature of the call based upon the input;

comparing the nature of the call to a statistical database; and

based upon the comparing, estimating the expected service time for the call.

15. The method of claim 11, wherein determining the threshold time comprises using a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

16. The method of claim 11, wherein determining the threshold time comprises using a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

17. The method of claim 11, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, and an expected total service time for a plurality of calls received in the first time interval.

18. The method of claim 17, further comprising determining a number of agents in a second group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, a total volume of a plurality of calls received in the first time interval, and the number of agents in the first group.

19. The method of claim 11, wherein determining the threshold time further comprises confirming that each of the average wait times in each of the plurality of queues is less than or equal to a predetermined maximum wait time for each of the plurality of queues.

20. A method of routing calls in a call center, comprising:

forecasting, by call activity forecaster, an anticipated call volume for each of a plurality of time intervals, wherein the forecasting is based upon historic call volume information;

receiving, by a communication port in the call center, a plurality of calls;

for each of the plurality of calls;

determining, by a threshold comparator, a threshold time as an indication of a maximum service time for the call, wherein the threshold time is based upon at least;

a first time interval during which the call was received,

the forecasted anticipated call volume for the first time interval,

a number of agents in each of a plurality of queues, the agents being assigned to answer incoming calls, and

average wait times in each of the plurality of queues,

wherein determining the threshold time comprises using a simulated annealing algorithm, wherein the simulated annealing algorithm comprises;

21. The method of claim 20, further comprising:

directing a second group of agents to place a return call to each caller that placed the call assigned to the second queue.

22. The method of claim 20, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group by a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

23. The method of claim 20, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

24. The method of claim 21, wherein directing the second group of agents to place the return call comprises determining a number of agents in the second group by a dynamic queue split algorithm, wherein the dynamic queue split algorithm comprises:

Minimize _{{T, S1, S2}}(J), subject to

S₁+S₂=S

W_R≦

Max(W_R)

W_c≦

Max(W_c) ,

wherein T is the threshold time, S1 is the number of agents in the first group, S2 is a number of agents in a second queue, S is a total number of agents, WR is an average wait time in the first queue, Max(WR) is a tolerable average wait time for the first queue, WC is an average wait time for in the second queue and Max(WC) is a tolerable average duration before callback.

25. The method of claim 21, wherein directing the second group of agents to place the return call comprises determining a number of agents in the second group by a simulated annealing algorithm, wherein the simulated annealing algorithm comprises:

26. The method of claim 20, wherein estimating the expected service time further comprises:

using an interactive voice response system to obtain an input from a caller placing the call;

determining the nature of the call based upon the input;

comparing the nature of the call to a statistical database; and

based upon the comparing, estimating the expected service time for the call.

27. The method of claim 20, wherein directing each call in the first queue of the plurality of queues to the first group of agents comprises determining a number of agents in the first group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, and an expected total service time for a plurality of calls received in the first time interval.

28. The method of claim 27, further comprising determining a number of agents in a second group based, at least in part, on a total number of agents, the forecasted anticipated call volume for the first time interval, a total volume of a plurality of calls received in the first time interval, and the number of agents in the first group.

29. The method of claim 20, wherein determining the threshold time further comprises confirming that each of the average wait times in each of the plurality of queues is less than or equal to a predetermined maximum wait time for each of the plurality of queues.

30. A system for routing calls, comprising:

a processor;

a non-transitory, processor-readable storage medium in operable communication with the processor;

a duration estimator in operable communication with the processor;

a call activity forecaster in operable communication with the processor;

a router in operable communication with the processor, wherein the router comprises a threshold comparator;

wherein the storage medium comprises one or more programming instructions that, when executed, cause the processor to;

direct the call activity forecaster to forecast an anticipated call volume for each of a plurality of time intervals, wherein the forecasting is based upon historic call volume information;

direct the communication port to receive a plurality of calls;

for each of the plurality of calls;

direct the threshold comparator to determine a threshold time as an indication of a maximum service time for the call, wherein the threshold time is based upon at least;

a first time interval during which the call was received,

the forecasted anticipated call volume for the first time interval,

a number of agents in each of a plurality of queues, the agents being assigned to answer incoming calls, and

average wait times in each of the plurality of queues,

wherein the threshold time is determined based on the use of a simulated annealing algorithm, wherein the simulated annealing algorithm comprises;

31. The system of claim 30, wherein the storage medium comprises one or more programming instructions that, when executed, further cause the processor to:

cause an interactive voice response system to obtain an input from each caller that placed the call assigned to the second queue;

determine the nature of each call based upon the input;

compare the nature of each call to a statistical database; and

based upon the comparing, estimate the expected service time for each call.

32. A system for routing calls, comprising:

a processor;

a non-transitory, processor-readable storage medium in operable communication with the processor;

a duration estimator in operable communication with the processor;

a call activity forecaster in operable communication with the processor;

a router in operable communication with the processor, wherein the router comprises a threshold comparator; and

a communications port in operable communication with the processor;

wherein the storage medium comprises one or more programming instructions that, when executed, cause the processor to;

direct the call activity forecaster to forecast an anticipated call volume for each of a plurality of time intervals, wherein the forecasting is based upon historic call volume information;

direct the communications port to receive a plurality of calls;

for each of the plurality of calls;

direct the threshold comparator to determine a threshold time as an indication of a maximum service time for the call, wherein the threshold time is based upon at least;

a first time interval during which the call was received,

the forecasted anticipated call volume for the first time interval,

a number of agents in each of a plurality of queues, the agents being assigned to answer incoming calls, and

average wait times in each of the plurality of queues,

wherein the threshold time is determined based on the use of a simulated annealing algorithm, wherein the simulated annealing algorithm comprises;