Research on feature fusion and multimodal patent text based on graph attention network

TL;DR

This paper introduces HGM-Net, a deep learning framework that enhances patent text analysis by integrating hierarchical learning, multi-modal graph attention, and sparse attention to improve feature fusion, semantic coherence, and efficiency.

Contribution

The study presents a novel deep learning framework combining hierarchical contrastive learning, multi-modal graph attention, and sparse attention for patent text analysis.

Findings

Outperforms existing methods in patent classification accuracy.

Improves semantic coherence in patent text mining.

Enhances efficiency in long text modeling.

Abstract

Aiming at the problems of cross-modal feature fusion, low efficiency of long text modeling and lack of hierarchical semantic coherence in patent text semantic mining, this study proposes HGM-Net, a deep learning framework that integrates Hierarchical Comparative Learning (HCL), Multi-modal Graph Attention Network (M-GAT) and Multi-Granularity Sparse Attention (MSA), which builds a dynamic mask, contrast and cross-structural similarity constraints on the word, sentence and paragraph hierarchies through HCL. Contrast and cross-structural similarity constraints are constructed at the word and paragraph levels by HCL to strengthen the local semantic and global thematic consistency of patent text; M-GAT models patent classification codes, citation relations and text semantics as heterogeneous graph structures, and achieves dynamic fusion of multi-source features by cross-modal gated attention; MSA adopts a hierarchical sparsity strategy to optimize the computational efficiency of long text modeling at word, phrase, sentence and paragraph granularity. Experiments show that the framework demonstrates significant advantages over existing deep learning methods in tasks such as patent classification and similarity matching, and provides a solution with both theoretical innovation and practical value for solving the problems of patent examination efficiency improvement and technology relevance mining.