Agent training sensitive call routing system

• US 7,110,525 B1
• Filed: 06/25/2002
• Issued: 09/19/2006
• Est. Priority Date: 06/25/2001
• Status: Expired due to Fees

• Current Assignee: Steven Mark Hoffberg, Toby Heller
• Original Assignee: Steven Mark Hoffberg, Toby Heller
• Inventors: Heller, Toby, Hoffberg, Steven M
• Primary Examiner(s): Deane, Jr., William J.
• Application Number:
  US10/180,763
• Time in Patent Office: 1,547 Days
• Field of Search: 37926501-26514, 37926601-2661
• US Class Current: 379/265.11
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision 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 3/5238 with waiting time or load prediction arrangements

Abstract

A call-management method and system for distributing calls to agents, wherein each agent has a profile, e.g., defining agent skills, efficiency, etc. The call center management system implements an algorithm for selecting an agent to receive a call to optimize caller utility, call center efficiency, and agent training. Therefore, the algorithm does not seek to necessarily route a call to the agent having the skill set most suited to the call; rather, the call may be routed to an agent who needs experience in the area of the call, and thus serves as a training exercise. Skilled agents may be made available to shadow the training agent when available.

Claims

1. A method of allocating a resource to handle a task, comprising the steps of:

(a) determining a task-handling load;

(b) identifying a characteristic of a task to be handled;

(c) in dependence on said determined task-handling load, selecting a handling protocol selected from the group consisting of;

(i) selecting a first trainable resource predicted to have deficient skills relating to the task based on the identified characteristic, while also selecting a second resource capable of assisting in training the first trainable resource with respect to the characteristic; and

(ii) selecting a third resource predicted to have sufficient skills relating to the task based on the identified characteristic,

wherein according to a selected protocol, a trainable resource is trained with respect to the at least one characteristic, or a sufficiently skilled resource handles the task.

2. The method according to claim 1, wherein the third resource has skills which are optimum for handling the task.

3. The method according to claim 2, wherein a plurality of tasks are simultaneously handled, and wherein a selected third resource has optimum skills with respect to the available resources and the identified characteristics of the tasks to be handled.

4. The method according to claim 1, wherein each resource has skills which are classified as a multidimensional vector, and wherein the identified task to be handled has a characteristic represented as a predicted multidimensional vector of required skills of a handling resource, wherein a selected first resource and second resource together have a composite multidimensional skill vector which substantially corresponds to the predicted multidimensional vector of required skills.

5. The method according to claim 1, wherein the trainable resource comprises a human.

6. The method according to claim 1, wherein the trainable resource comprises a call center agent.

7. The method according to claim 1, wherein the second resource has a training skill for remediating a skill deficiency with respect to the identified characteristic, such that after handling the task, the skills of the first resource are improved with respect to the identified characteristic.

8. The method according to claim 1, wherein a plurality of trainable first resources are available, wherein a particular first resource is selected based on which particular trainable first resource is predicted to have a maximum value gain in skills as a result of selection.

9. The method according to claim 1, wherein a plurality of second resources are available, wherein a particular second resource is selected based on which particular second resource is predicted to be able to impart a maximum value gain in skills as a result of selection.

10. The method according to claim 1, wherein a plurality of first and second resources are available, wherein a particular set of first and second resources are selected based on which set of first and second resources is predicted to have an optimum gain in skills for the first resource and lowest overall cost, as a result of selection of the set.

11. The method according to claim 1, wherein a selected first resource has a worst skill set for handling the task, selected from a group of first resources having sufficient skills for handling the task.

12. The method according to claim 1, wherein said selecting step comprises retrieving a resource profile, comprising a set of metrics corresponding to the set of identified characteristics.

13. The method according to claim 1, wherein a protocol selection is based on a threshold task-handling load for a group of resources.

14. The method according to claim 1, wherein resources are selected based on an optimum long-term cost utility of such selection, including training costs and anticipated future improvements in resource skills based on training opportunities.

15. The method according to claim 1, wherein said identification step comprises anticipating issues to be raised in handling the task, said selecting step comprising analyzing profile records of resources with respect to the anticipated issues to determine a minimum capability requirement, training requirement of a first resource, and a training capability of a second resource with respect to the anticipated issues, selecting a first resource having a skill exceeding the minimum capability requirement to handle the anticipated issues and having a training requirement with respect to the anticipated issues, and selecting a second resource having a training capability with respect to the anticipated issues, whereby a selected first and second resource have sufficient skills to handle the anticipated task, while the second resource assists the first resource in improving task handling capabilities.

16. The method according to claim 1, further comprising the step of updating a skill of a resource after selection thereof.

17. A method for determining an efficient schedule for a plurality of agents in a call center, balancing call center efficiency and agent training opportunity, each of the plurality of agents having a skill profile, comprising the steps of:

(a) predicting an aggregate set of characteristics for received calls handled during a contiguous period of time;

(b) selecting a set of agents having a target aggregate distribution of skills, including training agents having a skill set deficient with respect to the set of characteristics and trainer agents having a skill set permitting them to train the training agents with respect to the characteristics;

(c) scheduling the training agents and trainer agents for the contiguous period of time;

(d) determining a skill set required for handling a respective call; and

(e) dynamically pairing an available training agent and an available trainer agent for the respective call determined to require at least one skill for which the training agent is deficient and the trainer agent has a skill set permitting training of the training agent with respect to that at least one deficient skill, and for which the training agent and trainer agent together meet the determined skill set.

18. A method of improving agent skill sets, comprising the steps of:

(a) determining a skill profile of each of a set of agents;

(b) predicting a required skill profile of a communication;

(c) determining an anticipated surplus of agents for handling a predicted communication volume during the communication;

(d) selecting an available agent having a skill profile anticipated to be at least sufficient to handle the required skill profile of the communication, said skill profile being indicative of a lower level of skill with respect to at least one element of the required skill profile than at least one other available agent; and

(e) establishing a channel for the communication with the selected available agent and employing the communication as a training exercise.

19. The method according to claim 18, further comprising the step of maintaining performance metrics for the set of agents, said performance metrics being sensitive to said selection step, whereby a non-training performance rating of the selected agent is not impaired based on performance during the training exercise.

20. The method according to claim 18, wherein the skill profile is updated after the training exercise to represent a higher level of skill with respect to the required skill profile of the communication.

21. The method according to claim 18, wherein the skill profile is updated based on a utility of a communication.

22. The method according to claim 18, wherein said selecting is based on an optimization of the utility and cost of the communication, the agent training resulting from the training exercise being a component of the utility.

23. The method according to claim 18, wherein a communication routing is optimized based on a cost-utility function, said cost-utility function comprising a valuation of immediate costs and utilities and a valuation of persistent agent training costs and utilities.

24. A method of allocating a resource to handle a task, comprising the steps of:

(a) determining a capacity of a plurality of trainable task handling resources, each having a respective skill set;

(b) identifying at least one skill-requirement characteristic of a task to be handled; and

(c) in dependence on the determined capacity, the respective skill sets, and the skill requirement characteristic, selecting a task-handling protocol selected from the group consisting of;

(i) if the determined capacity indicates a surplus of trainable resources, availability of at least one first resource having a respective skill set deficient in skills corresponding to the at least one skill requirement characteristic, and availability of a second resource competent to train the first resource with respect to the at least one skill requirement, allocating the first resource, and the second resource to handle the task; and

(ii) otherwise, allocating a resource having a respective skill set sufficient to meet the skill requirement characteristic to handle the task.