Method for discovering problem agent behaviors

• US 20060271418A1
• Filed: 07/28/2005
• Published: 11/30/2006
• Est. Priority Date: 05/26/2005
• Status: Active Grant

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Hackbarth,, Kenneth R. Jr., Sobus, Katherine A., Kohler, Joylee E., Paddock, Henry R., Zanoni, David, Jenson, Murray
• Granted Patent: US 7,809,127 B2
• Time in Patent Office: Days
• US Class Current: 705/7
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/523 with call distribution or queueing

Abstract

A contact center is provided that includes a plurality of agents for servicing incoming contacts and a target behavior identification module operable to (i) process a set of events to yield a corresponding measure; (ii) compare the measure to a plurality of rule sets, each of the rule sets corresponding to a different type of target behavior; and (iii) when the measure is defined by the a selected rule set, associate the measure with a type of target behavior corresponding to the selected rule set.

Claims

1. In a contact center comprising a plurality of agents for servicing contacts, a method comprising:

processing a set of events to yield a corresponding measure across a set of dimensions;

comparing the measure to at least one rule set, the at least one rule set corresponding to a type of target behavior; and

when the measure is defined by the at least one rule set, associating the measure with the type of target behavior corresponding to the at least one rule set, wherein the set of events comprises a plurality of causally related events occurring at different times and wherein each rule set describes a plurality of dimensions.

2. The method of claim 1, wherein the at least one rule set is a plurality of rules sets and wherein each of the plurality of rule sets corresponds to a different type of target behavior.

3. The method of claim 2, wherein each event in the set of events temporally occurred consecutively and comprising:

determining a reason for the target behavior based on the plurality of causally related events.

4. The method of claim 3, wherein the set of events include a first event preceding the target behavior and a second event following the target behavior.

5. The method of claim 1, wherein the at least one rule set is a plurality of rules sets, wherein each of the plurality of rule sets corresponds to a different type of target behavior, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

summing, over a selected set of dimensions, the instances of each type of target behavior for each agent and for a grouping of agents.

6. The method of claim 4, wherein the instances are summed across all types of target behavior.

7. The method of claim 1, wherein the at least one rule set is a plurality of rules sets, wherein each of the plurality of rule sets corresponds to a different type of target behavior, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

displaying to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types;

receiving, from the user, a selection of a first field in the first display, the first field corresponding to a first type of target behavior; and

in response thereto, displaying to the user a second display comprising, for at least one of a selected agent and a grouping of agents, a number of historic instances of the first type of target behavior over prior time intervals.

8. The method of claim 1, wherein the at least one rule set is a plurality of rules sets, wherein each of the plurality of rule sets corresponds to a different type of target behavior, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

displaying to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types;

receiving, from the user, a selection of a first field in the first display, the first field corresponding to a first agent; and

in response thereto, displaying to the user a second display comprising, for the selected agent, a number of instances of each of the plurality of target behavior types occurring during a selected time interval.

9. The method of claim 8, further comprising:

receiving from the user a selection of a second field in the second display, the second field corresponding to a type of target behavior; and

in response thereto, displaying to the user a third display comprising additional details associated with the instances of the selected type of target behavior.

10. The method of claim 8, wherein the number of instances of each of the plurality of target behavior types are divided into at least one of contact type and distribution method.

11. The method of claim 1, wherein the at least one rule set is a plurality of rules sets, wherein each of the plurality of rule sets corresponds to a different type of target behavior, and further comprising:

selecting a threshold associated with the type of target behavior corresponding to the selected rule set;

determining whether at least one of a number of instances and total of durations of the number of instances has a first or a second type of relationship to the threshold;

when the first relationship exists, deeming the type of target behavior corresponding to the selected rule set to have occurred during a selected time interval; and

when the second relationship exists, not deeming the type of target behavior corresponding to the selected rule set to have occurred during the selected time interval.

12. The method of claim 1, wherein the at least one rule set is a plurality of rules sets, wherein each of the plurality of rule sets corresponds to a different type of target behavior, wherein the plurality of rule sets is at least twelve rule sets and wherein the target behaviors corresponding to the plurality of rule sets comprise a plurality of the following:

long contact, short contact, long alert, long initiate, long preview, long wrap up, short wrap up, transfer from, transfer in, blind transfer, transfer to a same routing point and/or queue, conference, redirect from agent rejection, redirect from time out, cancel from agent rejection, cancel from time out, agent release first, disconnect from hold, long hold, hold time, short aux, aux time, aux working time, aux non-working time, wrap up time, direct time, internal time, short contact-then-aux, short contact-then-logout, login-then-aux, short and long contacts side-by-side, variation in active time, repeated conference with a selected person, repeated transfer to a selected person, and variation in wrap up time.

13. A computer readable medium comprising executable instructions for performing the steps of claim 1.

14. In a contact center comprising a plurality of agents for servicing contacts, a method comprising:

processing a set of events to yield a corresponding measure across a set of dimensions;

comparing the measure to a plurality of rule sets, each of the rule sets corresponding to a different type of target behavior; and

when the measure is defined by the a selected rule set, associating the measure with a type of target behavior corresponding to the selected rule set.

15. The method of claim 14, wherein the set of events comprises a plurality of causally related events occurring at different times, wherein each rule set describes a plurality of dimensions, wherein each event in the set of events temporally occurred consecutively and further comprising:

determining a reason for the target behavior based on the plurality of causally related events.

16. The method of claim 14, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

summing, over a selected set of dimensions, the instances of each type of target behavior for each agent and for a grouping of agents.

17. The method of claim 14, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

displaying to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types;

receiving, from the user, a selection of a first field in the first display, the first field corresponding to a first type of target behavior; and

in response thereto, displaying to the user a second display comprising, for at least one of a selected agent and a grouping of agents, a number of historic instances of the first type of target behavior over prior time intervals.

18. The method of claim 14, wherein a plurality of event sets are defined by a plurality of target behavior types and further comprising:

displaying to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types;

receiving, from the user, a selection of a first field in the first display, the first field corresponding to a first agent; and

in response thereto, displaying to the user a second display comprising, for the selected agent, a number of instances of each of the plurality of target behavior types occurring during a selected time interval.

19. The method of claim 18, further comprising:

receiving from the user a selection of a second field in the second display, the second field corresponding to a type of target behavior; and

in response thereto, displaying to the user a third display comprising additional details associated with the instances of the selected type of target behavior.

20. The method of claim 18, wherein the number of instances of each of the plurality of target behavior types are divided into at least one of contact type and distribution method.

21. The method of claim 14, further comprising:

selecting a threshold associated with the type of target behavior corresponding to the selected rule set;

determining whether at least one of a number of instances and total of durations of the number of instances has a first or a second type of relationship to the threshold;

when the first relationship exists, deeming the type of target behavior corresponding to the selected rule set to have occurred during a selected time interval; and

when the second relationship exists, not deeming the type of target behavior corresponding to the selected rule set to have occurred during the selected time interval.

22. The method of claim 14, wherein the plurality of rule sets is at least twelve rule sets and wherein the target behaviors corresponding to the plurality of rule sets comprise a plurality of the following:

long contact, short contact, long alert, long initiate, long preview, long wrap up, short wrap up, transfer from, transfer in, blind transfer, transfer to a same routing point and/or queue, conference, redirect from agent rejection, redirect from time out, cancel from agent rejection, cancel from time out, agent release first, disconnect from hold, long hold, hold time, short aux, aux time, aux working time, aux non-working time, wrap up time, direct time, internal time, short contact-then-aux, short contact-then-logout, login-then-aux, short and long contacts side-by-side, variation in active time, and variation in wrap up time.

23. A computer readable medium comprising executable instructions for performing the steps of claim 14.

24. A contact center comprising:

a plurality of agents for servicing incoming contacts; and

a target behavior identification module operable to process a set of events to yield a corresponding measure across a set of dimensions;

compare the measure to a plurality of rule sets, each of the rule sets corresponding to a different type of target behavior; and

, when the measure is defined by the a selected rule set, associate the measure with a type of target behavior corresponding to the selected rule set.

25. The method of claim 24, wherein the set of events comprises a plurality of causally related events occurring at different times, wherein each rule set describes a plurality of dimensions, and wherein each event in the set of events temporally occurred consecutively and wherein the module is further operable to determine a reason for the target behavior based on the plurality of causally related events.

26. The method of claim 24, wherein a plurality of event sets are defined by a plurality of target behavior types, wherein the module is further operable to sum, over a selected time interval, the instances of each type of target behavior for each agent and for a grouping of agents and wherein the module is further operable to display to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types and the sums;

receive, from the user, a selection of a first field in the first display, the first field corresponding to a first type of target behavior; and

in response thereto, display to the user a second display comprising, for at least one of a selected agent and a grouping of agents, a number of historic instances of the first type of target behavior over prior time intervals.

27. The method of claim 24, wherein a plurality of event sets are defined by a plurality of target behavior types and wherein the module is further operable to display to a user a first display comprising, for each of the plurality of agents, a number of instances of each of the plurality of target behavior types;

receive, from the user, a selection of a first field in the first display, the first field corresponding to a first agent;

in response thereto, display to the user a second display comprising, for the selected agent, a number of instances of each of the plurality of target behavior types occurring during a selected time interval;

receive from the user a selection of a second field in the second display, the second field corresponding to a type of target behavior; and

, in response to the selection of the second field, display to the user a third display comprising additional details associated with the instances of the selected type of target behavior, wherein the number of instances of each of the plurality of target behavior types are divided into at least one of contact type and distribution method.

28. The method of claim 24, wherein the module is further operable to select a threshold associated with the type of target behavior corresponding to the selected rule set;

determine whether at least one of a number of instances and total of durations of the number of instances has a first or a second type of relationship to the threshold;

when the first relationship exists, deem the type of target behavior corresponding to the selected rule set deemed to have occurred during a selected time interval; and

when the second relationship exists, not deem the type of target behavior corresponding to the selected rule set to have occurred during the selected time interval.

29. The method of claim 24, wherein the plurality of rule sets is at least twelve rule sets and wherein the target behaviors corresponding to the plurality of rule sets comprise a plurality of the following:

long contact, short contact, long alert, long initiate, long preview, long wrap up, short wrap up, transfer from, transfer in, blind transfer, transfer to a same routing point and/or queue, conference, redirect from agent rejection, redirect from time out, cancel from agent rejection, cancel from time out, agent release first, disconnect from hold, long hold, hold time, short aux, aux time, aux working time, aux non-working time, wrap up time, direct time, internal time, short contact-then-aux, short contact-then-logout, login-then-aux, short and long contacts side-by-side, variation in active time, and variation in wrap up time.