A multi-modal fusion-based sentiment analysis method and system
By fusing facial expressions, voice, EEG signals, and visual pulse signals through a multi-layer deep learning network, the problem of insufficient fusion strategies in multimodal sentiment analysis is solved, and high-precision and robust sentiment analysis is achieved that adapts to complex environments and individual differences.
Patent Information
- Application Number
- CN202411303810.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2025-10-17
- Estimated Expiration
- 2044-09-19
AI Technical Summary
Existing multimodal sentiment analysis methods have deficiencies in feature fusion and context awareness, resulting in poor robustness of sentiment analysis in complex environments, low personalized recognition accuracy, and the inability to fully tap the potential value of multimodal information.
A multi-layer deep learning network is used to fuse facial expressions, voice, EEG signals and visual pulse signals. Through multi-head attention mechanism, adaptive weighting, bidirectional long short-term memory network, multi-scale causal convolutional network and graph neural network, combined with dynamic weight adjustment and context perception mechanism, dynamic fusion of multimodal data is achieved.
It improves the accuracy and robustness of sentiment analysis, enhances the system's adaptability in different environments and individual situations, and achieves global understanding and personalized recognition of emotional states.