Telephone traffic abnormity detection method and device

Abstract

The invention provides a telephone traffic abnormity detection method and device. The method includes the following steps: a historical trend threshold regular calculation step: cleaning historical telephone traffic data and regularly calculating a historical trend threshold on the basis of the cleaned historical telephone traffic data; a historical threshold detection step; a real-time trend detection step: calculating a real-time trend threshold on the basis of telephone traffic data ahead of a current detection point within a first period of time, and detecting whether the current telephonetraffic quantity exceeds the real-time trend threshold; a historical trend detection step: detecting whether the current telephone traffic quantity exceeds the historical trend threshold; and a warning sending step: if the current telephone traffic quantity exceeds a historical threshold, the real-time trend threshold and the historical trend threshold, sending out warning information. On the basis of detection of the historical threshold, real-time trend detection and historical trend detection are added, thereby overcoming the disadvantage of warning setting through direct collection of historical telephone traffic quantity and improving the accuracy of telephone traffic abnormality detection.

Description

technical field [0001] The invention relates to the field of call traffic management, in particular to a traffic anomaly detection method and equipment thereof. Background technique [0002] The call center has a large amount of real-time traffic data every day, and these real-time data need to be monitored to ensure the normal operation of the call center business. The current monitoring method uses historical threshold alarms. Although the problem of relying on manual setting of alarm rules has been solved to a certain extent, there are still defects. [0003] Historical threshold alarms can be used to directly collect historical traffic statistics to obtain historical thresholds. However, only directly collecting historical traffic does not consider the impact of accidental factors on the data. The sudden traffic caused by accidental factors does not reflect the real Traffic regularity will interfere with the accuracy of traffic forecasting. For example, during holidays...

AI Technical Summary

Problems solved by technology

The current monitoring method uses historical threshold alarms. Although the problem of relying on manual setting of alarm rules has been solved to a certain extent, there are still defects.

[0003] Historical threshold alarms can be used to directly collect historical traffic statistics to obtain historical thresholds. However, only directly collecting historical traffic does not consider the impact of accidental factors on the data. The sudden traffic caused by accidental factors does not reflect the real traffic rules, which will interfere with the accuracy of traffic forecasting

For example, during holidays, the traffic volume tends to be higher than usual. When detecting the historical threshold of the holiday traffic volume, an alarm is often triggered when the traffic volume exceeds the historical threshold. In fact, the trend of these traffic volumes Not much has changed, it's normal and this has led to a lot of false positives

Such false alerts negatively impact call traffic management

Images