Voice classification method and device and storage medium

The invention provides a voice classification method and device and a storage medium, relates to the technical field of data processing, and can solve the problem that the accuracy and efficiency of voice classification are low. The method comprises the following steps: extracting an initial text co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: JIAO JUNNAN, CHENG JIRUN, ZENG XUEMEI, YANG ZONGLIN, LIU XUEWU
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 a voice classification method and device and a storage medium, relates to the technical field of data processing, and can solve the problem that the accuracy and efficiency of voice classification are low. The method comprises the following steps: extracting an initial text corresponding to a target call record; adopting a large language model to remove error characters in the initial text to obtain a target text; under the condition that the target text contains the preset keyword, the target classification model is adopted to analyze the target text, a target probability value is obtained, and the target probability value is used for representing the possibility that the target text belongs to the target type; under the condition that the target probability value is larger than a first preset threshold value, a large language model is adopted to classify the target text, a target classification result is obtained, and the target classification result is used for indicating whether the