System and method for automated performance monitoring for a call servicing system

• US 8,175,253 B2
• Filed: 07/07/2005
• Issued: 05/08/2012
• Est. Priority Date: 07/07/2005
• Status: Expired due to Fees

• Current Assignee: SBC Knowledge Ventures LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Knott, Benjamin Anthony, Bushey, Robert R., Martin, John Mills
• Primary Examiner(s): SHAH, ANTIM G
• Application Number:
  US11/176,972
• Publication Number:
  US 20070025528A1
• Time in Patent Office: 2,497 Days
• Field of Search: 379/265.06, 379/265.07, 379/265.08, 379/266.08, 379/32.01, 379/33, 379/265.02, 379/265.03
• US Class Current: 379/265.03
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/10 Providing fault- or trouble-signals
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends

Abstract

A system and method for monitoring and reporting automated call-processing performance is disclosed. Initially, performance metrics can be established for normal or acceptable system performance. Performance metrics may be determined for individual components and/or a combination of components in a system, wherein the individual metric may help to provide a performance indicator for the call processing system. The performance metrics can be established by utilizing historical data gathered from past operating characteristics or operating parameters. The performance metric can be calculated from past operating characteristics and could be a statistical distribution or a statistical value. This statistical distribution will often conform to a Gaussian distribution also known as a bell curve. However, acceptable performance limits can be set based on nearly any statistical distribution. A monitor can collect data over a predetermined time interval and process the monitored data to provide a “near” real-time performance data. When the near real time performance data falls within a pre-defined range of normal operation (based on the statistical distribution) system operation is most likely acceptable and operation proceeds. However, when the system performance data is outside of a normal range of operation, beyond a performance metric or exceeds a threshold value an alarm can be set to notify a human or an electronic device.

Claims

1. A method of monitoring an automated call processing system comprising:

monitoring a plurality of operating parameters;

maintaining a first count of first statistical values associated with a first operating parameter of the plurality of operating parameters;

maintaining a second count of second statistical values associated with a second operating parameter of the plurality of operating parameters;

weighting a first performance metric established from the first count associated with the first operating parameter differently than a second performance metric established from the second count associated with the second operating parameter;

adding the first weighted performance metric to the second weighted performance metric to establish a third performance metric, wherein the third performance metric is established based on a time sample of historical data collected from past operational characteristics of a call processing center, and wherein the time sample is adjusted to filter data;

establishing a threshold associated with the third performance metric;

tracking a performance indicator in near real time;

detecting a deviation between the performance indicator and the third performance metric; and

triggering an alarm when the detected deviation exceeds the threshold.

2. The method of claim 1, wherein the plurality of operating parameters includes at least one of:

an average call duration, a system response time, a premature disconnect count, a verbal extensible mark up language server access time, a caller hang up rate, an excessive confirmation rate, and a false acceptance rate.

3. The method of claim 1, further comprising transmitting a message responsive to an alarm trigger.

4. The method of claim 1, wherein the third performance metric is a mean of the historical data and the threshold is based on at least one of a standard deviation and a z-score developed from the historical data.

5. The method of claim 4, wherein the alarm is triggered when the performance indicator is greater than or less than plus or minus one (1) standard deviation or a z-score unit from the mean of the historical data.

6. The method of claim 1, further comprising comparing the performance indicator and the third performance metric on a periodic basis.

7. The method of claim 1, wherein the performance indicator is based on activities related to one of an interactive voice response system, a speech recognition module, and a voice extensible mark up language server.

8. The method of claim 1, wherein the alarm is triggered when the detected deviation indicates one of a locked up component and a power outage.

9. The method of claim 1, wherein a subsequent caller is routed to an agent when the detected deviation exceeds the threshold.

10. A system for monitoring performance of a call center, the system comprising:

an interactive voice response system configured to accept spoken caller input and to process a call responsive to the spoken caller input;

a server coupled to the interactive voice response system, the server configured to supply executable objects to the interactive voice response system; and

a monitor coupled to the interactive voice response system, the monitor configured to;

monitor a combination of a plurality of operating parameters of the interactive voice response system related to caller activity;

maintain a first count of first statistical values associated with a first operating parameter;

maintain a second count of second statistical values associated with a second operating parameter;

weight a first performance metric established from the first count associated with the first operating parameter differently than a second performance metric established from the second count associated with the second operating parameter;

add the first weighted performance metric to the second weighted performance metric to determine a third performance metric;

maintain the third performance metric based on a time sample of historical data for the combination of the plurality of operating parameters; and

detect a deviation between the combination of the plurality of operating parameters and the third performance metric, wherein the time sample is adjusted to filter data resulting from known abnormal events to prevent the known abnormal events from skewing a data distribution.

11. The system of claim 10, wherein at least one of the plurality of operating parameters includes at least one of:

a call time duration, a caller hang up, and a delay time.

12. The system of claim 10, further comprising a database coupled to the monitor and configured to store information associated with the at least one of the plurality of operating parameters.

13. The system of claim 12, further comprising a statistical processor configured to calculate one of an actual mean, an actual standard deviation, an actual range, and an actual median for the stored information.

14. The system of claim 13, further comprising calculating one of the actual mean, the actual standard deviation, the actual range, and the actual median utilizing data from approximately a previous half hour time period.

15. The system of claim 10, further comprising an alarm generator configured to trigger an alarm when the detected deviation exceeds a threshold.

16. The system of claim 10, further comprising a switch for switching a caller to a human operator when the detected deviation exceeds a threshold.

17. A non-transitory computer readable storage medium embodying a program of instructions to manipulate a computing platform to:

combine statistical data associated with a plurality of operating parameters of a call processing center to establish a third performance metric by;

maintaining a first count of first statistical values associated with a first operating parameter of the plurality of operating parameters;

maintaining a second count of second statistical values associated with a second operating parameter of the plurality of operating parameters; and

weighting a first performance metric established from the first count associated with the first operating parameter differently than a second performance metric established from the second count associated with the second operating parameter; and

adding the first weighted performance metric to the second weighted performance metric, wherein the third performance metric is established based on a time sample of historical data, and wherein the time sample is adjusted to filter data;

track an actual performance of a combination of the plurality of operating parameters in near real time;

detect a deviation between the third performance metric and the actual performance; and

trigger an alarm when the detected deviation exceeds a threshold.

18. The non-transitory computer readable storage medium of claim 17, wherein at least one of the plurality of operational parameters includes at least one of:

an average call duration, a system response time, a premature disconnect count, a voice extensible mark up language server access time, a caller hang up rate, an excessive confirmation rate, and a false acceptance rate.

19. The non-transitory computer readable storage medium of claim 17, further comprising instructions to manipulate the computing platform to transmit a message when the detected deviation exceeds the threshold.

20. The non-transitory computer readable storage medium of claim 17, further comprising instructions to switch a caller to a human operator when the detected deviation exceeds the threshold.