Filters








7,570 Hits in 3.6 sec

Recommending patents based on latent topics

Ralf Krestel, Padhraic Smyth
2013 Proceedings of the 7th ACM conference on Recommender systems - RecSys '13  
In this paper we investigate techniques to automatically recommend patents given a query patent.  ...  We investigate the use of latent Dirichlet allocation and Dirichlet multinomial regression to represent patent documents and to compute similarity scores.  ...  .$15.00. patents based on punch cards was developed [3] .  ... 
doi:10.1145/2507157.2507232 dblp:conf/recsys/KrestelS13 fatcat:2tl74fa4lbex7oyd2yemraspny

Identifying Technology Opportunities Based on Internal Capabilities and Technical Suitability

Junhyeok Park, Seung-Jun Shin, Pyunghoi Koo, Wonchul Seo
2018 ICIC Express Letters  
There have been many studies on technology opportunities, but most of the studies did not consider internal capabilities of the enterprise or exclude entry barriers to the recommended technology opportunities  ...  Therefore, this study proposes a methodology for analyzing internal capabilities through a patent portfolio held by the enterprise and recommending feasible technology opportunities in terms of technology  ...  conducting text mining based on the patent portfolio of enterprise.  ... 
doi:10.24507/icicel.12.06.599 fatcat:btzkkm5sgbf47p2okyi4pxdzg4

Cross-domain citation recommendation based on hybrid topic model and co-citation selection

Supaporn Tantanasiriwong, Sumanta Guha, Paul Janecek, Choochart Haruechaiyasak, Leif Azzopardi
2017 International Journal of Data Mining Modelling and Management  
This paper proposes an approach for cross-domain citation recommendation based on the Hybrid Topic Model and Co-Citation Selection.  ...  2017) Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection. International Journal of Data Mining, Modelling and Management, 9 (3).  ...  d , and i z represents a latent topic over word distribution in a given document.  ... 
doi:10.1504/ijdmmm.2017.086566 fatcat:pqoywmyf7nf3fop7pge5rf5jhi

Cross-domain citation recommendation based on hybrid topic model and co-citation selection

Leif Azzopardi, Choochart Haruechaiyasak, Sumanta Guha, Paul Janecek, Supaporn Tantanasiriwong
2017 International Journal of Data Mining Modelling and Management  
This paper proposes an approach for cross-domain citation recommendation based on the Hybrid Topic Model and Co-Citation Selection.  ...  2017) Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection. International Journal of Data Mining, Modelling and Management, 9 (3).  ...  d , and i z represents a latent topic over word distribution in a given document.  ... 
doi:10.1504/ijdmmm.2017.10007657 fatcat:6belfatx5fh57d742cufaf5ccm

Identifying Potential Technology Themes Based on Internal Capabilities Using Topic Modeling and Association Rule Mining

Jusung Kim, Woon-Seek Lee, Sungchul Choi, Wonchul Seo
2016 Innovative Computing Information and Control Express Letters, Part B: Applications  
technology classes by utilizing ARM and topic modeling technique.  ...  However, these methods have not considered the possibility of realization or only discovered technical opportunities such as the entry of a large set of patent classification codes.  ...  Latent Dirichlet allocation (LDA). LDA, one of the topic modeling techniques proposed by Blei et al. , is a probabilistic model to extract the major topic groups in a word corpus [10] .  ... 
doi:10.24507/icicelb.07.10.2267 fatcat:dcgzlrnrx5dphlzoioyaxnyqga

Patent partner recommendation in enterprise social networks

Sen Wu, Jimeng Sun, Jie Tang
2013 Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13  
model based on inventors' feedback.  ...  We evaluate our proposed model on large enterprise patent networks.  ...  The patent partner recommendation is then made based on the similarity score. Collaborative Filtering (CF): it leverages the exist-ing co-invention relationships to make the recommendation.  ... 
doi:10.1145/2433396.2433404 dblp:conf/wsdm/WuST13 fatcat:lfmxlk3fqbhbri7vovil5wk4ja

Measuring the drafting alignment of patent documents using text mining

Davit Khachatryan, Brigitte Muehlmann, William Speier
2020 PLoS ONE  
The measure is defined for each patent document by first identifying the latent topics underlying the claims and the specification, and then using the Hellinger distance to find the proximity between the  ...  topical coverages.  ...  Assuming the existence of T latent topics throughout the pre-processed corpus, LDA is applied to uncover the latent topics based on matrix M.  ... 
doi:10.1371/journal.pone.0234618 pmid:32649675 fatcat:sfyftmzwajdc7hy4qb7a4z5iua

A Study on the Deduction and Diffusion of Promising Artificial Intelligence Technology for Sustainable Industrial Development

Hong Joo Lee, Hoyeon Oh
2020 Sustainability  
Based on the rapid development of Information and Communication Technology (ICT), all industries are preparing for a paradigm shift as a result of the Fourth Industrial Revolution.  ...  Eleven topics were extracted via topic modeling.  ...  Here, 9556 patent documents were collected and refined based on five criteria (Table 3) . Thus, words were extracted in noun units from the abstract of the patent.  ... 
doi:10.3390/su12145609 fatcat:n7ecat632zdyxawxsg6mia2fm4

Technology Hotspot Tracking: Topic Discovery and Evolution of China's Blockchain Patents Based on a Dynamic LDA Model

Jinli Wang, Yong Fan, Hui Zhang, Libo Feng
2021 Symmetry  
First, we propose a time-based dynamic latent Dirichlet allocation (TDLDA) modeling method based on a probabilistic graph model and knowledge representation learning for patent text mining.  ...  In this paper, we use topic modeling, topic intensity, and evolutionary computing models to discover research hotspots and development trends in the field of blockchain patents.  ...  Acknowledgments: This research was part of the project of "Research on Distributed Technology Resource System and Service Evaluation Technology", 2017-2020.  ... 
doi:10.3390/sym13030415 doaj:46bb11ba600e44f6b224bb8a4e36beb4 fatcat:x2df3fd5pzhfnlqh2uito65xt4

Comparison and Evaluation of Different Methods for the Feature Extraction from Educational Contents

Jose Aguilar, Camilo Salazar, Henry Velasco, Julian Monsalve-Pulido, Edwin Montoya
2020 Computation  
use cases: in an information retrieval context and in an educational recommendation system.  ...  The feature extraction methods used in this paper are the Best Matching 25 (BM25), the Latent Semantic Analysis (LSA), Doc2Vec, and the Latent Dirichlet allocation (LDA).  ...  Feature Extraction Strategies Based on Probabilities: LDA Latent Dirichlet allocation (LDA) is a probabilistic model based on unsupervised learning, which supposes each document like a mix of topics,  ... 
doi:10.3390/computation8020030 fatcat:lowlzbys3rbrvegz5xq5untht4

Efficient Nearest-Neighbor Search in the Probability Simplex

Kriste Krstovski, David A. Smith, Hanna M. Wallach, Andrew McGregor
2013 Proceedings of the 2013 Conference on the Theory of Information Retrieval - ICTIR '13  
Topic models, which have served as versatile tools for exploratory data analysis and visualization, represent documents as probability distributions over latent topics.  ...  Health (NIH) grants and prior-art retrieval for patents.  ...  We then map each patent into a latent topic space using LDA.  ... 
doi:10.1145/2499178.2499189 dblp:conf/ictir/KrstovskiSWM13 fatcat:in5bkm2ezzh6vi47aed33w2ymm

Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey [article]

Hamed Jelodar, Yongli Wang, Chi Yuan, Xia Feng, Xiahui Jiang, Yanchao Li, Liang Zhao
2018 arXiv   pre-print
Also, we summarize challenges and introduce famous tools and datasets in topic modeling based on LDA.  ...  There are various methods for topic modeling, which Latent Dirichlet allocation (LDA) is one of the most popular methods in this field.  ...  This model used a topic model based on Correspondence Latent Dirichlet Allocation (Corr-LDA).  ... 
arXiv:1711.04305v2 fatcat:jzsx6owjyjfo3gkbohrc2ggkzq

WordNet Sense Disambiguation Based Patent Search

S.R Janani, C Sathya, S Poornima
2014 IOSR Journal of Computer Engineering  
We have used PoS tagger and SynSets from WordNet for identifying the intention of the user for the given search keyword and to create relevant partitions based on the Synsets.  ...  To address this problem, we propose a new user-friendly patent search method which focuses on both Effectiveness and Efficiency of the patent search method.  ...  For improving efficiency patent is partition into small partitions based on their topics and classes.  ... 
doi:10.9790/0661-16684852 fatcat:drefzsr6b5fhfpwoqzlaazc6wi

Chronological Citation Recommendation with Time Preference [article]

Shutian Ma, Heng Zhang, Chengzhi Zhang, Xiaozhong Liu
2021 arXiv   pre-print
To explore chronological citation recommendation, this paper wants to predict the time preference based on user queries, which is a probability distribution of citing papers published in different time  ...  Although, some researchers have investigated chronological citation recommendation by adding time related function or modeling textual topics dynamically.  ...  Mahdabi et al. proposed a patent citation recommendation model which employs time-aware random walk on the weighted patent citation network (Mahdabi & Crestani, 2014) .  ... 
arXiv:2101.07609v1 fatcat:zmlky6w5efga5n2gkzu5ti42pa

Thematic exploration of YouTube data: A methodology for discovering latent topics

2017 Muma Business Review  
This research method is proposing proposes a framework that can be used by researchers and practitioners to discover latent topics found within a target set of YouTube video transcript documents.  ...  All of these studies can be aggregated together to describe the problem that continues to challenge researchers and information management practitioners whom are attempting to explore a latent set of topics  ...  Then the researchers screened a sample of 50 YouTube videos based on the technique recommended by the research method.  ... 
doi:10.28945/4202 fatcat:kf2pbztqgnartixsbqvdbctexm
« Previous Showing results 1 — 15 out of 7,570 results