Edge text classification method based on virtual words and TF-IDF

The invention provides an edge text classification method based on virtual words and TF-IDF (term frequency-inverse document frequency), which can be suitable for the text classification problem in an edge environment with limited resources and unstable network information, and comprises the followi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHAO KANKAN, ZHU YONG, BEN TINGTING, XIE RONGPING, CHENG QING, MA LEIMING
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 provides an edge text classification method based on virtual words and TF-IDF (term frequency-inverse document frequency), which can be suitable for the text classification problem in an edge environment with limited resources and unstable network information, and comprises the following steps: constructing an edge collaboration mode which mainly comprises an edge cloud and an edge tail end; establishing a synchronization mechanism at each node; performing text segmentation through a virtual word segmentation method; performing text word segmentation based on a word segmentation dictionary algorithm; and performing text classification based on a TF-IDF algorithm. By the adoption of the method, the large text is segmented into the small texts, the text word segmentation algorithm is optimized, the text classification efficiency can be effectively improved, the resource occupancy rate is reduced, the method is more suitable for the resource-limited edge environment, and the requirement for efficie