Delivery information quality prediction model training method, information delivery method and device

Delivery information quality prediction model training method, information delivery method and device

The invention relates to a delivery information quality prediction model training method and device and an information delivery method and device. The delivery information quality prediction model training method comprises the steps of obtaining multiple items of delivered information and return dat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHAO XIMO, LI JUNJIE, XIAO YAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
PHYSICS
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention relates to a delivery information quality prediction model training method and device and an information delivery method and device. The delivery information quality prediction model training method comprises the steps of obtaining multiple items of delivered information and return data of each item of delivered information in an initial delivery stage; determining a sample attribute of each item of released information based on the return data; the sample attributes comprise positive samples and negative samples; wherein the quality score of the delivered information with the positive sample attribute is higher than the quality score of the delivered information with the negative sample attribute; and determining material features of each item of released information, and training a preset machine learning model based on the material features of each item of released information and the sample attributes of each item of released information to obtain a released information quality prediction mo