Retransmission number prediction method and retransmission number prediction device
The invention discloses a retransmission number prediction method and a retransmission number prediction device. The retransmission number prediction method comprises the following steps. A plurality of data sets respectively corresponding to a plurality of user devices are obtained, and the data se...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a retransmission number prediction method and a retransmission number prediction device. The retransmission number prediction method comprises the following steps. A plurality of data sets respectively corresponding to a plurality of user devices are obtained, and the data sets are dimensionally reduced into a plurality of custom feature sets. Dividing the custom feature sets into a training set and a test set, and determining a plurality of first transmittable samples from the training set by using a classification algorithm; grouping the first transmittable samples into a plurality of first groups by using a grouping algorithm, the first groups respectively corresponding to a plurality of different retransmission times, and generating a retransmission times prediction model by using the first groups;
本发明公开一种重传次数预测方法和重传次数预测装置。重传次数预测方法包括下列步骤。取得分别对应于多个用户设备的多个数据集合,并且将该些数据集合降维为多个自定义特征集合。将该些自定义特征集合分为训练集以及测试集,并且使用分类演算法从训练集中决定出多个第一可传输样本。使用分组演算法将该些第一可传输样本分组为多个第一群组,该些第一群组分别对应于不同的多个重传次数,并且使用该些第 |
---|