| 引用本文: | 李大川,忻展红.大型呼叫中心人工呼入量的最小二乘支持向量机模型[J].控制理论与应用,2009,26(7):815~818.[点击复制] |
| LI Da-chuan,XIN Zhan-hong.Large call-centers’ arrival-rates prediction models based on the least squares support vector machine[J].Control Theory and Technology,2009,26(7):815~818.[点击复制] |
|
| 大型呼叫中心人工呼入量的最小二乘支持向量机模型 |
| Large call-centers’ arrival-rates prediction models based on the least squares support vector machine |
| 摘要点击 1609 全文点击 992 投稿时间：2008-06-11 修订日期：2008-09-18 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2009.7.CCTA080598 |
| 2009,26(7):815-818 |
| 中文关键词 呼叫中心 预测 最小二乘支持向量机 |
| 英文关键词 call center forecasting least squares support vector machine theory(LS-SVM) |
| 基金项目 国家自然科学基金资助项目(70473006) |
|
| 中文摘要 |
| 通过分析大型呼叫中心人工呼入量的数据特点, 文中将呼入量分解为日呼入量与相应时间段呼入量, 利用最小二乘支持向量机(LS-SVM)的原理, 建立日呼入量与时间段呼入量两个时间序列预测模型. 实验仿真证明, 采用该方法建立的日呼入量与时间段呼入量预测模型, 在回归和预测方面都可以得到满意的结果. 通过与神经网络预测模型的对比分析, LS-SVM总体上优于人工神经网络的预测效果. |
| 英文摘要 |
| In analyzing the data from a large call center, we find that arrival rates can be split into the daily-arrival-rate and the time-period-arrival-rate. Based on the least squares support vector machine theory(LS-SVM), predicting models of the daily-arrival-rate and the time-period-arrival-rate are established. Simulation experiments show that these models are good at regression and forecasting. Compared with Back-Propagation(BP) neural network prediction models, these models give better prediction results. |