Scholarlink

<p>This study introduces HI-ICD-AugCCE, a hybrid framework that integrates structural and semantic analysis of patent claims using deep learning techniques. By assigning importance weights to individual claims based on hierarchical position and information density, the framework effectively captures the core technical content within patent texts. It further employs an unsupervised contrastive learning model enhanced with data augmentation, enabling accurate similarity evaluation even in the absence of labeled data. Experiments demonstrate that HI-ICD-AugCCE achieves a Spearman correlation of 0.812, representing a 6.98% improvement over baselines. The results highlight the framework’s effectiveness in enhancing the semantic precision and scalability of patent similarity assessment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

What matters in patent claims: structural and semantic-based feature extraction and embedding optimization

  • 期刊论文

  • 发表日期：

    2025年9月29日

查看全文
  • Xinyu Tong,
  • Linrong Zeng,
  • Yonghe Lu

摘要

This study introduces HI-ICD-AugCCE, a hybrid framework that integrates structural and semantic analysis of patent claims using deep learning techniques. By assigning importance weights to individual claims based on hierarchical position and information density, the framework effectively captures the core technical content within patent texts. It further employs an unsupervised contrastive learning model enhanced with data augmentation, enabling accurate similarity evaluation even in the absence of labeled data. Experiments demonstrate that HI-ICD-AugCCE achieves a Spearman correlation of 0.812, representing a 6.98% improvement over baselines. The results highlight the framework’s effectiveness in enhancing the semantic precision and scalability of patent similarity assessment.