Patent collaborative filtering recommendation approach based on patent similarity

Xiang, Ji; Gu, Xinjian; Dai, Feng; Chen, Jixi; Le, Chengyi

doi:10.1109/fskd.2011.6019821

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Personalized patent searches enrich retrieval results by utilizing semantic information in patent classification, textual descriptions and external knowledge. For example, to filter patents for enterprises, Ji et al (2011) utilized semantic information in patent classification to enhance conventional CF. To address term mismatches when retrieving prior art to a patent application, Mahdabi et al (2013) Recommending patent citations helps patent examiners identify prior information relevant to patent applications efficiently and effectively.…”

Section: Patent Recommendationmentioning

confidence: 99%

“…Moreover, a large proportion of high-quality patents are held by research institutions and have not been transferred. For solving these problems, state-of-the-art patent recommendation methods leverage rich information in patent documents to identify matched patents in different contexts, such as filtering patents for personalized retrieval, suggesting patent citations and recommending patents for potential buyers (Ji et al, 2011;Oh et al, 2013;Rui and Min, 2016;Wang et al, 2019b;Wu et al, 2013). Most of these existing methods focus on improving the recommendation accuracy while ignoring the interpretability of recommendation results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging online behaviors for interpretable knowledge-aware patent recommendation

Yan

Zhang

et al. 2021

INTR

View full text Add to dashboard Cite

PurposePatent 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/approachFirst, 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.FindingsExperiments 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/valueA 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.

show abstract

Section: Patent Recommendationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Leveraging online behaviors for interpretable knowledge-aware patent recommendation

Yan

Zhang

et al. 2021

INTR

View full text Add to dashboard Cite

show abstract

“…CF recommendation recommends patents to users according to their similar interests, and the recommendation sets can be extended unlike with topic model-based methods . Ji et al [12] calculated the similarity between patents with the patent model tree, on the basis of which conventional CF can be improved by filling a sparse user rating matrix with patent similarity. Trappey et al [13] clustered users with similar patent search behaviours to identify users’ neighbours and inferred new patent recommendations based on intercluster group member behaviours and characteristics.…”

Section: Related Workmentioning

confidence: 99%

“…Automatic patent recommendation has been investigated in many contexts such as personalised patent retrieval, patent citation recommendation and patent trading recommendation [7][8][9]. Previous studies mainly used topic models [10,11] and collaborative filtering (CF) methods [12,13] for patent recommendation. Given the advantages of cutting-edge techniques in capturing relations between potential patent buyers and candidate patents, graph analysis [14,15] and deep neural networks (DNNs) [16] were introduced to improve patent trading recommendation.…”

Section: Introductionmentioning

confidence: 99%

Sequential patent trading recommendation using knowledge-aware attentional bidirectional long short-term memory network (KBiLSTM)

Jiang

et al. 2021

Journal of Information Science

View full text Add to dashboard Cite

With the rapid development of the patent marketplace, patent trading recommendation is required to mitigate the technology searching cost of patent buyers. Current research focuses on the recommendation based on existing patents of a company; a few studies take into account the sequential pattern of patent acquisition activities and the possible diversity of a company’s business interests. Moreover, the profiling of patents based on solely patent documents fails to capture the high-order information of patents. To bridge the gap, we propose a knowledge-aware attentional bidirectional long short-term memory network (KBiLSTM) method for patent trading recommendation. KBiLSTM uses knowledge graph embeddings to profile patents with rich patent information. It introduces bidirectional long short-term memory network (BiLSTM) to capture the sequential pattern in a company’s historical records. In addition, to address a company’s diverse technology interests, we design an attention mechanism to aggregate the company’s historical patents given a candidate patent. Experimental results on the United States Patent and Trademark Office (USPTO) data set show that KBiLSTM outperforms state-of-the-art baselines for patent trading recommendation in terms of F1 and normalised discounted cumulative gain (nDCG). The attention visualisation of randomly selected company intuitively demonstrates the recommendation effectiveness.

show abstract

A Method for Calculating Patent Similarity Using Patent Model Tree Based on Neural Network

Zhao

2018

Advances in Brain Inspired Cognitive Systems

View full text Add to dashboard Cite

Patent collaborative filtering recommendation approach based on patent similarity

Cited by 9 publications

References 8 publications

Leveraging online behaviors for interpretable knowledge-aware patent recommendation

Leveraging online behaviors for interpretable knowledge-aware patent recommendation

Sequential patent trading recommendation using knowledge-aware attentional bidirectional long short-term memory network (KBiLSTM)

A Method for Calculating Patent Similarity Using Patent Model Tree Based on Neural Network

Contact Info

Product

Resources

About