Multi-mode question and answer method and system based on emotion recognition and large language model

The invention belongs to the technical field of intelligence, and discloses a multi-mode question answering method and system based on emotion recognition and a large language model. The method comprises the following steps: acquiring a preprocessed question and answer pair voice data set; construct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: MA QINQIN, YU XINGLIANG, PAN XIANZHEN
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 belongs to the technical field of intelligence, and discloses a multi-mode question answering method and system based on emotion recognition and a large language model. The method comprises the following steps: acquiring a preprocessed question and answer pair voice data set; constructing a question and answer knowledge graph, a voice text recognition model, a voice emotion recognition model, a text emotion recognition model and a large language model; performing text emotion recognition based on the text question-answering mode; performing intelligent response generation according to the prediction text emotion label; voice text and voice emotion recognition is carried out based on the voice question and answer mode; performing intelligent response generation according to the predicted voice emotion label; and text-to-speech conversion is carried out. The system comprises a training data acquisition unit, a model construction unit, a user interaction unit, a text question-answering unit, a voic