|
|
|
| Research on the Technical Similarity Visualization Based on word2vec and LDA Topic Model |
| Xi Xiaowen1, Guo Ying2, Song Xinna3, Wang Jin3 |
1.Archives of Chinese Academy of Sciences, Beijing 100190
2.Business School, China University of Political Science and Law, Beijing 100088
3.School of Management & Economics, Beijing Institute of Technology, Beijing 100081 |
|
|
|
|
Abstract Technical similarity is an important part of technical intelligence analysis of enterprises, organizations, or countries, which can provide accurate and effective information for identifying potential competitive relationships and partners. Aiming at the problem that the LDA topic model ignores the semantic correlation between patent context, this paper proposes a technical similarity visualization method based on word2vec and LDA topic model. First, based on the word2vec model, we learn the contextual information of feature words in the collection of patent documents, and based on the LDA topic model, we construct the probability distribution of patentee-patent-technology topic and generate the topic vector, patent document vector, and patentee vector at the level of “word granularity.” We then use vector similarity index to calculate semantic similarity between patentee, and on this basis, the patentee-technology subject network is constructed. Finally, taking NEDD (nano enabled drug delivery) as an example, the model is proved to be effective in the analysis of technology similarity measure.
|
|
Received: 04 June 2019
|
|
|
|
1 Cloodt M, Hagedoorn J, van Kranenburg H. Mergers and acquisitions: their effect on the innovative performance of companies in high-tech industries[J]. Research Policy, 2006, 35(5): 642-654.
2 Arts S, Cassiman B, Gomez J C. Text matching to measure patent similarity[J]. Strategic Management Journal, 2018, 39(1): 62-84.
3 Jaffe A B. Technological opportunity and spillovers of R&D: evidence from firms' patents, profits and market value[J]. The American Economic Review, 1986, 76(5): 984-1001.
4 Jaffe A B, Trajtenberg M. International knowledge flows: evidence from patent citations[J]. Economics of Innovation and New Technology, 1999, 8(1/2): 105-136.
5 蔡虹, 孙顺成, 陈蓉. 我国与主要创新型国家(地区)技术相似度的测算分析[J]. 西安交通大学学报(社会科学版), 2009, 29(5): 1-6.
6 Kogler D F, Rigby D L, Tucker I. Mapping knowledge space and technological relatedness in US cities[J]. European Planning Studies, 2013, 21(9): 1374-1391.
7 Lai K K, Wu S J. Using the patent co-citation approach to establish a new patent classification system[J]. Information Processing & Management, 2005, 41(2): 313-330.
8 张曦, 王贤文, 刘则渊, 等. 基于专利计量的企业技术相似性网络测度研究[J]. 情报杂志, 2011, 30(1): 90-93.
9 Huang M H, Chiang L Y, Chen D Z. Constructing a patent citation map using bibliographic coupling: a study of Taiwan's high-tech companies[J]. Scientometrics, 2003, 58(3): 489-506.
10 Lo S C. Patent coupling analysis of primary organizations in genetic engineering research[J]. Scientometrics, 2008, 74(1): 143-151.
11 洪勇, 李英敏. 基于专利耦合的企业间技术相似性可视化研究[J]. 科学学研究, 2013, 31(7): 1013-1021.
12 Yoon B, Park Y. A systematic approach for identifying technology opportunities: keyword-based morphology analysis[J]. Technological Forecasting and Social Change, 2005, 72(2): 145-160.
13 彭继东, 谭宗颖. 一种基于文本挖掘的专利相似度测量方法及其应用[J]. 情报理论与实践, 2010, 33(12): 114-118.
14 张端阳, 肖国华, 李文燕. 面向专利集成的专利技术相关性测度方法研究[J]. 情报杂志, 2014, 33(11): 54-61.
15 Li C Z, Guo J Y, Lu Y, et al. LDA meets Word2Vec: a novel model for academic abstract clustering[C]// Companion Proceedings of the Web Conference 2018. Geneva: International World Wide Web Conferences Steering Committee, 2018: 1699-1706.
16 Xu Y H, Guo X T, Hao J X, et al. Combining social network and semantic concept analysis for personalized academic researcher recommendation[J]. Decision Support Systems, 2012, 54(1): 564-573.
17 徐红姣, 曾文, 张运良. 基于Word2vec的论文和专利主题关联演化分析方法研究[J]. 情报杂志, 2018, 37(12): 36-42.
18 张金柱, 于文倩, 刘菁婕, 等. 基于网络表示学习的科研合作预测研究[J]. 情报学报, 2018, 37(2): 132-139.
19 Zhou X, Porter A L, Robinson D K R, et al. Nano-enabled drug delivery: a research profile[J]. Nanomedicine: Nanotechnology, Biology and Medicine, 2014, 10(5): e889-e896.
20 Shrestha S, Wu J, Sah B, et al. X-ray induced photodynamic therapy with copper-cysteamine nanoparticles in mice tumors[J]. Proceedings of the National Academy of Sciences of the United States of America, 2019, 116(34): 16823-16828. |
|
|
|
