Leveraging online behaviors for interpretable knowledge-aware patent recommendation

doi:10.1108/INTR-08-2020-0473

	Leveraging online behaviors for interpretable knowledge-aware patent recommendation
	Du, Wei 3; Yan, Qiang 2; Zhang, Wenping 3; Ma, Jian 1
刊名	INTERNET RESEARCH
	2021-06-11
页码	20
关键词	Interpretable knowledge-aware recommendation Patent recommendation Online behaviors
ISSN号	1066-2243
DOI	10.1108/INTR-08-2020-0473
英文摘要	Purpose Patent trade recommendations necessitate recommendation interpretability in addition to recommendation accuracy because of patent transaction risks and the technological complexity of patents. This study designs an interpretable knowledge-aware patent recommendation model (IKPRM) for patent trading. IKPRM first creates a patent knowledge graph (PKG) for patent trade recommendations and then leverages paths in the PKG to achieve recommendation interpretability. Design/methodology/approach First, we construct a PKG to integrate online company behaviors and patent information using natural language processing techniques. Second, a bidirectional long short-term memory network (BiLSTM) is utilized with an attention mechanism to establish the connecting paths of a company - patent pair in PKG. Finally, the prediction score of a company - patent pair is calculated by assigning different weights to their connecting paths. The semantic relationships in connecting paths help explain why a candidate patent is recommended. Findings Experiments on a real dataset from a patent trading platform verify that IKPRM significantly outperforms baseline methods in terms of hit ratio and normalized discounted cumulative gain (nDCG). The analysis of an online user study verified the interpretability of our recommendations. Originality/value A meta-path-based recommendation can achieve certain explainability but suffers from low flexibility when reasoning on heterogeneous information. To bridge this gap, we propose the IKPRM to explain the full paths in the knowledge graph. IKPRM demonstrates good performance and transparency and is a solid foundation for integrating interpretable artificial intelligence into complex tasks such as intelligent recommendations.
资助项目	National Natural Science Foundation of China[71901208] ; National Natural Science Foundation of China[71771212] ; National Natural Science Foundation of China[U1711262] ; National Natural Science Foundation of China[71801217] ; Humanities and Social Sciences Foundation of the Ministry of Education[18YJC630025] ; Key Projects of Philosophy and Social Sciences Research of Chinese Ministry of Education[19JZD021] ; Ministry of Education, Science and Technology Development Center[2019J01010]
WOS研究方向	Business & Economics ; Computer Science ; Telecommunications
语种	英语
出版者	EMERALD GROUP PUBLISHING LTD
WOS记录号	WOS:000660627500001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17668]
专题	中国科学院计算技术研究所
通讯作者	Zhang, Wenping
作者单位	1.City Univ Hong Kong, Coll Business, Informat Syst, Hong Kong, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Renmin Univ China, Sch Informat, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Du, Wei,Yan, Qiang,Zhang, Wenping,et al. Leveraging online behaviors for interpretable knowledge-aware patent recommendation[J]. INTERNET RESEARCH,2021:20.
APA	Du, Wei,Yan, Qiang,Zhang, Wenping,&Ma, Jian.(2021).Leveraging online behaviors for interpretable knowledge-aware patent recommendation.INTERNET RESEARCH,20.
MLA	Du, Wei,et al."Leveraging online behaviors for interpretable knowledge-aware patent recommendation".INTERNET RESEARCH (2021):20.