Keyword generation method based on optimal transmission theory

The invention discloses a keyword generation method based on an optimal transmission theory, as shown in Figure 1, the method comprises the following steps: step 1, data preprocessing; step 2, constructing a loss function; step 3, model training; and 4, testing and evaluating the model. According to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YIN GUOSHUN, YANG PENG, YAO YU, ZHAO GUANGZHEN
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 keyword generation method based on an optimal transmission theory, as shown in Figure 1, the method comprises the following steps: step 1, data preprocessing; step 2, constructing a loss function; step 3, model training; and 4, testing and evaluating the model. According to the method, the loss function is constructed based on the optimal transmission theory, the text semantic information capturing capability of the model is enhanced, so that the model can generate keywords better fitting text semantics, missing keywords irrelevant to or even inconsistent with the text semantics are reduced, and the keyword quality is improved. 本发明公开了一种基于最优传输理论的关键词生成方法,如图1所示,方法包括以下步骤:步骤1:数据预处理;步骤2:损失函数构建;步骤3:模型训练;步骤4:模型测试与评估。本发明基于最优传输理论构建损失函数,加强模型捕获文本语义信息的能力,进而使得模型能够生成更加贴合文本语义的关键词,降低与文本语义无关甚至相悖的缺失关键词的出现,提升关键词的质量。