| 引用本文: | 赖培源,卢伊虹,廖德章,王昌栋,戴青云,赖剑煌.基于多模态异质图网络的专利推荐算法.软件学报,2026,37(5):1964-1981 |
| |
|
| |
|
|
| 本文已被：浏览 2353次 下载 1173次 |
码上扫一扫！ |
|
|
| 基于多模态异质图网络的专利推荐算法 |
|
赖培源1,2,3, 卢伊虹4, 廖德章1, 王昌栋4,3, 戴青云2,3, 赖剑煌4
|
|
1.广东省华南技术转移中心有限公司, 广东 广州 511458;2.广东工业大学 信息工程学院, 广东 广州 510006;3.广东省知识产权大数据重点实验室, 广东 广州 510665;4.中山大学 计算机学院, 广东 广州 510006
|
|
| 摘要: |
| 通过专利推荐将科技创新成果转化为现实生活中的实际应用, 让科学技术实现经济价值, 对社会经济发展具有重大意义. 然而, 现有的专利推荐算法往往忽略了专利本身所包含的多模态信息, 导致推荐结果无法全面反映专利的真实价值与应用潜力, 进而影响专利与企业需求之间的匹配精度. 为此, 提出了一种基于多模态异质图网络的专利推荐算法(multimodal heterogeneous graph network for patent recommendation, MHGN). 首先, 利用预训练表征模型将专利的多属性文本信息与图像以及企业信息进行初始化表征学习. 随后, 采用图注意力网络学习企业在不同模态下的偏好表征, 在此基础上, 进一步基于偏好表征的相似度学习企业-专利交互的关系权重, 并设计了一个图卷积网络来学习企业和专利的节点偏好表征. 最后, 引入了适配向量, 并使用注意力机制对节点偏好表征与多模态表征进行融合. 在实验验证上, 构建了4个真实的高校向企业转让的专利数据集, 并与7个先进的基线模型进行了实验对比, 结果表明, 所提模型在各项指标上均显著优于基线模型. |
| 关键词: 专利推荐 多模态 异质图 技术转移 适配向量 |
| DOI：10.13328/j.cnki.jos.007537 |
| 分类号:TP181 |
| 基金项目:国家自然科学基金(62276277); 广东省技术转移智能匹配工程技术研究中心项目(2022A175); 广东省知识产权大数据重点实验室(2018B030322016) |
|
| Patent Recommendation Algorithm Based on Multimodal Heterogeneous Graph Network |
|
LAI Pei-Yuan1,2,3, LU Yi-Hong4, LIAO De-Zhang1, WANG Chang-Dong4,3, DAI Qing-Yun2,3, LAI Jian-Huang4
|
|
1.Guangdong South China Technology Commercialization Center Co. Ltd., Guangzhou 511458, China;2.School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China;3.Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangzhou 510665, China;4.School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
|
| Abstract: |
| The transformation of scientific and technological innovations into practical applications through patent recommendation is of great significance for realizing the economic value of science and technology and promoting socio-economic development. However, existing patent recommendation algorithms often overlook the multimodal information embedded in patents, leading to recommendation results that fail to comprehensively reflect the value and application potential of patents. Consequently, this affects the accuracy of matching patents with the needs of companies. To address this issue, this study proposes a multimodal heterogeneous graph network for patent recommendation (MHGN). The proposed method first utilizes pre-trained models to initialize the representation of multimodal information, including the textual and image attributes of patents as well as company information. Then, a graph attention network is employed to learn the preference representations of companies across different modalities. Based on this, the relationship weights of company-patent interactions are further learned based on the similarity of preference representations, and a graph convolutional network is designed to learn the node preference representations of companies and patents. Finally, to better integrate the multimodal information, an adaptation vector is introduced and an attention mechanism is used to fuse the node preference representations with multimodal representations. In addition, four real-world patent datasets from university-to-company transfers are constructed, and experiments are conducted comparing the proposed model with seven advanced baseline models. The results demonstrate that the proposed model significantly outperforms the baselines across all evaluation metrics. |
| Key words: patent recommendation multimodal heterogeneous graph technology commercialization adaptation vector |
|
|
|
|
