Model construction optimization method and device and computer readable storage medium

The invention discloses a model construction optimization method and device and a computer readable storage medium, the method is applied to a first device, and the method comprises the following steps: using first feature data corresponding to each first training sample as network input, and using...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WU YIFAN, ZHUANG QING, CHEN QINGLIN, CHEN TING, WU SANPING, ZHUANG WEILIANG, TAN YUNKUN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a model construction optimization method and device and a computer readable storage medium, the method is applied to a first device, and the method comprises the following steps: using first feature data corresponding to each first training sample as network input, and using reconstruction of the first feature data as a training target for training to obtain a self-encoding network; inputting the second feature data corresponding to each second training sample into an encoder in the self-encoding network for encoding to obtain feature encoding data corresponding to each second training sample; and sending the feature coding data as desensitized second feature data to a second device, so that the second device performs training by adopting the feature coding data corresponding to each second training sample and combining the tag data corresponding to each second training sample to obtain a target prediction model. According to the method, a model construction optimization scheme based o