基于主题发现的专利发明人推荐方法  

Patent Inventor Recommendation Method Based on Topic Discovery

作　　者：黎楠[1] 杜永萍[1] 何明[1] Li Nan Du Yongping He Ming(College Of Computer Science And Technology, Beijing University Of Technology, Beijing, 100124)

机构地区：[1]北京工业大学计算机学院,北京100124

出　　处：《情报工程》2015年第3期90-97,共8页Technology Intelligence Engineering

基　　金：国家科技支撑计划子课题(2013BAH21B02-01);北京市自然科学基金资助项目(4153058);上海市智能信息处理重点实验室开放基金(IIPL-2014-004)

摘　　要：LDA主题模型可用于识别大规模文档集中潜藏的主题信息,本文提出了一种基于LDA建立发明人兴趣主题模型的方法,合并每位发明人的专利数据,专利信息基于发明人进行划分,将标准的文档-主题-词的三层LDA模型变为专利数据中的发明人-主题-词的发明人兴趣模型,实现发明人的主题发现,并利用该模型中主题分布之间的相似性进行发明人的个性化推荐。在采集真实专利数据集上的实验结果表明该方法相比传统的向量空间模型方法和隐马尔科夫模型方法具有更高的准确率,推荐效果更优。LDA model can be used for identifying topic information from large-scale document set. We propose the approach to build the inventor topic model based on LDA, which divides patent data based on inventor and represents each inventor with the ownedpatents. The standard three layers of document-topic-word in LDA（Latent Dirichlet Allocation） model becometheinventor topic model of inventor-topic-word. The topics of the inventor are discovered and recommendation is implementbased on thesimilarity of topic distribution. Experiment on real data set shows that the new approach has a better performance compared to the traditional Vector Space Model method and Hidden Markov Model method.

关 键 词：LDA主题模型 专利 主题发现 推荐技术 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]