Agent training sensitive call routing system

• US 7,916,858 B1
• Filed: 09/18/2006
• Issued: 03/29/2011
• Est. Priority Date: 06/25/2001
• Status: Expired due to Fees

• Current Assignee: Patent Armory Inc. (Jeffrey M. Gross)
• Original Assignee: Steven Mark Hoffberg, Toby Heller
• Inventors: Heller, Toby, Hoffberg, Steven M.
• Primary Examiner(s): DEANE JR, WILLIAM J
• Application Number:
  US11/532,883
• Time in Patent Office: 1,653 Days
• Field of Search: 37926501-26514, 37926601-2661, 379/309
• US Class Current: 379/265.12
• 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 plurality of resources to handle a plurality of concurrent tasks, comprising the steps of:

(a) predicting a load of concurrent tasks to be handled during a forthcoming period;

(b) identifying at least one characteristic of each respective task to be handled;

(c) determining a set of resources available for handling concurrent tasks during the forthcoming period, each resource having at least one resource characteristic relating to its efficiency in handling a respective task in dependence on the respective at least one characteristic; and

(d) in dependence on at least a relationship of each of a predicted load of tasks to be concurrently handled during the forthcoming period, the determined availability of resources for handling the concurrent tasks, a utility of each respective task to be handled, and a cost of each available resource, selecting, with an automated processor, an optimum association of at least one resource to handle each respective concurrent task, at least one resource handling a respective task having an efficiency of handling tasks per unit time below that of a most efficient available resource.

2. The method according to claim 1, wherein at least two resources are selected to handle a single task, at least one of which is competent by itself to handle the task.

3. The method according to claim 1, wherein at least two resources are selected to handle a single task, at least one of which is incompetent by itself to handle the task.

4. The method according to claim 1, wherein the selected at least one resource is an optimum set for handling the task based on available resources.

5. The method according to claim 2, wherein a plurality of tasks are concurrently handled, and wherein a selection of resources to handle concurrent tasks is optimized to minimize an immediate cost function of the available resources.

6. The method according to claim 2, wherein an allocation of resources to handle concurrent tasks is optimized to minimize a long-term cost function sensitive to resource experience and training.

7. The method according to claim 1, wherein each resource has skills which are classified as a multidimensional vector, and wherein each task to be handled has a characteristic represented as a predicted multidimensional vector of required skills of a respective at least one handling resource, wherein the at least one selected resource for a respective task together have a composite multidimensional skill vector which exceeds the predicted multidimensional vector of required skills with respect to each dimension of the predicted multidimensional vector.

8. The method according to claim 1, wherein the at least one resource comprises a human.

9. The method according to claim 1, wherein the at least one resource comprises a call center agent.

10. The method according to claim 1, wherein a plurality of resources are selected for handling at least one task, one of the selected resources being a trainer and another of the selected resources being a trainee.

11. The method according to claim 1, wherein at least one resource is selected based on a predicted increase in skills as a result of selection thereof.

12. The method according to claim 1, wherein an adaptation of a resource characteristic of a selected resource is assigned an economic value, a plurality of resources are selected to concurrently handle a task, and a particular set of resources is selected seeking an optimum adaptation of resource characteristics and lowest overall cost, as a result of selection of the set of resources to handle the concurrent tasks.

13. The method according to claim 1, wherein said selecting comprises retrieving a resource profile, comprising a set of metrics corresponding to the set of characteristics of selected resources.

14. The method according to claim 1, wherein a plurality of selection protocols are predefined, and a protocol selected from said plurality of protocols based a relationship of a predicted load of concurrent tasks to be handled and an availability of resources for handling tasks.

15. The method according to claim 1, wherein resources are selected based on an optimum long-term cost utility of such selection, including adaptation costs and anticipated future adaptations based on predicted task handling opportunities.

16. The method according to claim 1, further comprising the step of updating a resource profile record after selection of a respective selected resource based on at least a predicted adaptation of the respective selected resource.

17. A system for allocating a resource to handle a task, comprising:

(a) an input for receiving information characterizing at least one task to be handled;

(b) a memory storing characteristics of a set of resources available for handling tasks, each resource having at least one resource characteristic relating to its efficiency in handling a respective task, the at least one resource characteristic having adaptive task and training by a separate resource; and

(c) an automated processor for selecting an optimum association of at least one resource from the set of resources to handle the task, wherein the selected resource has an efficiency, defined as task handling capacity over time, below that of a most efficient available resource, in dependence on each of;

a relationship of a predicted load of tasks to be concurrently handled,

an availability of resources for handling concurrent tasks,

a utility of handling the task, and

a cost of allocating an available resource.

18. The system according to claim 17, further comprising a queue for storing identifiers of tasks to be handled.

19. The system according to claim 17, wherein the processor updates the memory based on a prediction of an adaptation of the at least one resource after handling the task.

20. A computer readable medium storing non-transitory instructions for controlling an automated processor to communicate an allocation of at least one available resource to handle at least one task, comprising the steps of:

(a) receiving information characterizing at least one task to be handled;

(b) storing task handling characteristics of a set of resources, each resource having at least one task handling characteristic relating to its efficiency in terms of ability to handle respective tasks over time; and

(c) selecting, in dependence on a relationship of;

a predicted load of tasks to be handled,

an availability of resources for handling tasks,

a predicted resulting utility of handling the task, and

a predicted cost of allocating an available resource to a respective task,

at least one resource to selected handle a task having an efficiency in terms of task handling capacity per unit time, below that of a most efficient available resource.