Feature generation method and device, nonvolatile storage medium and processor
The invention discloses a feature generation method and device, a nonvolatile storage medium and a processor. The method comprises the following steps: acquiring original data of a target object, and processing the original data to obtain target data; according to the target data, feature metadata c...
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 feature generation method and device, a nonvolatile storage medium and a processor. The method comprises the following steps: acquiring original data of a target object, and processing the original data to obtain target data; according to the target data, feature metadata capable of generating features are set, and the features are input features of a machine learning model used for modeling the target object; setting feature statements capable of generating features according to the feature metadata; and executing the feature statements by using a structured query language to generate features. The technical problems that time and labor are consumed due to the fact that input features needed by a machine learning model are obtained through manual arrangement of original data at present, and the arranged data are difficult to reuse are solved.
本申请公开了一种特征生成方法及装置、非易失性存储介质、处理器。其中,该方法包括:获取目标对象的原始数据,并对原始数据进行处理,得到目标数据;根据目标数据,设置可生成特征的特征元数据,其中,特征为用于对目标对象进行建模的机器学习模型的输入特征;根据特征元数据,设置可生成特征的特征语句; |
---|