Filters








14,912 Hits in 4.9 sec

Hybrid-patent classification based on patent-network analysis

Duen-Ren Liu, Meng-Jung Shih
2010 Journal of the American Society for Information Science and Technology  
This study proposes a hybrid-patent-classification approach that combines a novel patent-network-based classification method with three conventional classification methods to analyze query patents and  ...  To further improve the approach, we combine it with content-based, citation-based, and metadata-based classification methods to develop a hybrid-classification approach.  ...  prediction based on patent-network analysis and the modified kNN classifier.  ... 
doi:10.1002/asi.21459 fatcat:sic7ubt4b5b2jeqpbpndaty7i4

Open Relation Extraction in Patent Claims with a Hybrid Network

Boting Geng, Wenqing Wu
2021 Wireless Communications and Mobile Computing  
triples from patent claims with a hybrid neural network architecture based on multihead attention mechanism.  ...  patent content mining, patent retrieval, and patent knowledge base constructions.  ...  On the other hand, statistical-based machine learning is frequently applied for processing patent analysis in recent years.  ... 
doi:10.1155/2021/5547281 fatcat:mduxto5zzzacfanawwrbg4acay

Technological Landscape and Collaborations in Hybrid Vehicles Industry

Marisela Rodríguez, Francisco Paredes
2015 Foresight and STI Governance  
Evidence from leaders in the development of hybrid vehicles demonstrates the productivity of the methodology for analyzing patent data developed by the authors.  ...  The global prospects of this process can be estimated by systematically analyzing patents outlined in international patent databases.  ...  Emphasis of research based on the top Derwent Class Codes (DCC) We also determined the patent categories based on the standard Derwent Innovations Index classification.  ... 
doi:10.17323/1995-459x.2015.2.6.21 fatcat:fc75ixdzv5fr3befiasdww2l2y

Solar cell patent classification method based on keyword extraction and deep neural network [article]

Yongmin Yoo, Dongjin Lim, Tak-Sung Heo
2021 arXiv   pre-print
To solve the solar cell patent classification problem, we propose a keyword extraction method and a deep neural network-based solar cell patent classification method.  ...  Finally, we use a deep neural network-based solar cell patent classification model to classify power patents, and the training accuracy is greater than 95%.  ...  Through classification experiments, we know that hybrids of different methods can give good results in patent classification of deep neural networks.  ... 
arXiv:2109.08796v3 fatcat:a5vh4fyssnf3zbxlhqdb24agku

Deduction of Vacant Technology through Patent Analysis in Disaster-Safety Positioning Technologies

Hangwon Lee, Youngok Kim
2013 International Journal of Disaster Recovery and Business Continuity  
based on the geo-spatial information.  ...  In this paper, it is intended to understand the existing R&D status on the positioning technology field from the patent perspective through performing patent analysis on the disaster-safety positioning  ...  Figure 6 shows the flow of changing technologies according to the patent application year based on 2-nd level classification.  ... 
doi:10.14257/ijdrbc.2013.4.04 fatcat:i72df7rm5nan3eczkzqbbezgvm

PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT [article]

Hamid Bekamiri, Daniel S. Hain, Roman Jurowetzki
2021 arXiv   pre-print
based on text data.  ...  We deploy our framework for classification with a simple Nearest Neighbors (KNN) model that predicts Cooperative Patent Classification (CPC) of a patent based on the class assignment of the K patents with  ...  Third, we propose a hybrid model based on transformers and traditional ML models that outperforms the current state-of-the-art in text-based multi-label and multi-class patent classification.  ... 
arXiv:2103.11933v3 fatcat:fnizp37sjrh3takauds2ftqjsi

Improving the Discovery of Technological Opportunities Using Patent Classification Based on Explainable Neural Networks

Tadeusz, Michal
2021 EUROPEAN RESEARCH STUDIES JOURNAL  
Purpose: The paper aims to present an approach supporting the improvement of technological opportunities discovery using patent classification based on explainable neural networks.  ...  In this study, a proposal for an approach enables the discovery of technological opportunities using patent classification based on explainable neural networks.  ...  Conclusions Earlier studies focused mainly on reducing the difficulties associated with discovering technological opportunities using patent classification based on various neural networks through applying  ... 
doi:10.35808/ersj/2361 fatcat:npbemjrvlndt3jcdhjrr56khoy

Patent-based QFD framework development for identification of emerging technologies and related business models: A case of robot technology in Korea

Yonghan Ju, So Young Sohn
2015 Technological forecasting & social change  
The proposed QFD framework consists of a hierarchical structure with three house-of-quality (HOQ) stages, which are based on patent analysis and opinions of specialists and generalists.  ...  Based on the results of the HOQ and the convergence of iterated correlation analysis, prospective technology was identified.  ...  QFD and patent network analysis The QFD framework is used to identify technical requirements in future markets [26] .  ... 
doi:10.1016/j.techfore.2014.04.015 fatcat:u3ewymwp4vfmziqgjrag4eas6y

The state-of-the-art on Intellectual Property Analytics (IPA): A literature review on artificial intelligence, machine learning and deep learning methods for analysing intellectual property (IP) data

Leonidas Aristodemou, Frank Tietze
2018 World Patent Information  
Recently, there have been substantial developments in the field of patent analytics, which describes the science of analysing large amounts of patent information to discover trends.  ...  In this paper, we contribute to the ongoing discussion on the use of intellectual property analytics methods, i.e artificial intelligence methods, machine learning and deep learning approaches, to analyse  ...  [64] construct a predictive patent analysis model, based on social network analysis and decision tress, for technology transfer.  ... 
doi:10.1016/j.wpi.2018.07.002 fatcat:cawnmevwcna2zep7z6ikixwzgu

A hybrid method to trace technology evolution pathways: a case study of 3D printing

Ying Huang, Donghua Zhu, Yue Qian, Yi Zhang, Alan L. Porter, Yuqin Liu, Ying Guo
2017 Scientometrics  
In this paper, we apply co-classification analysis to reveal the technical evolution process of a certain technical field, using co-word analysis to extract implicit or unknown patterns and topics, and  ...  We illustrate this hybrid approach with 3D printing, referring to various technologies and processes used to synthesize a three-dimensional object.  ...  Co-classification Analysis based on Patent Classification Decision-making activities of knowledge-intensive enterprises depend heavily on the successful classification of patents, which is a reflection  ... 
doi:10.1007/s11192-017-2271-8 fatcat:k67mz627f5bqhj5nl5zq2ej5au

Patent Registration Prediction Methodology Using Multivariate Statistics

Won-Gyo JUNG, Sang-Sung PARK, Dong-Sik JANG
2011 IEICE transactions on information and systems  
In this paper, we propose a novel patent registration method based on patent data.  ...  Whether a patent is registered or not is usually based on the subjective judgment of the patent examiners.  ...  This analysis is based on the frequency of the patent index [16] .  ... 
doi:10.1587/transinf.e94.d.2219 fatcat:pzkqqzmb2je3lna4ujmoiyjxju

Clearing the Fog of Anticancer Patents from 1993–2013: Through an In-Depth Technology Landscape & Target Analysis from Pioneer Research Institutes and Universities Worldwide

Ajay Dara, Abhay T. Sangamwar, Wolfgang Glanzel
2014 PLoS ONE  
In addition, the results have also addressed the target analysis, leading inventor, assignee, collaboration network, geographical distribution, patent trend analysis, citation maps and technology assessment  ...  Methodology/Principal Findings: The methodology include quantitative and qualitative assessment based on the bibliometric parameters and manual technology categorisation to understand the changing patent  ...  Contributed reagents/materials/analysis tools: AD. Contributed to the writing of the manuscript: AD ATS.  ... 
doi:10.1371/journal.pone.0103847 pmid:25083710 pmcid:PMC4118965 fatcat:2mtoyfis7fee7pbdxoa4dbyyfa

Guest Editorial: Tech Mining for Engineering Management: An Introduction

Yi Zhang, Ying Huang, Denise Chiavetta, Alan L. Porter
2021 IEEE transactions on engineering management  
CTI-Oriented Patent Analysis Patent data have long been one of the key ST&I sources for gaining CTI, and facilitating patent statistics, including unique attributes [e.g., international patent classification  ...  Competitors' Innovation Activities: Analyzing the Competitive Patent Landscape Based on Semantic Anchor Points, in which the authors specifically focused on the activities of patent assignees and proposed  ... 
doi:10.1109/tem.2021.3061862 fatcat:kudqaewka5hd5p5qvq3sqqvfgy

A literature review on the state-of-the-art in patent analysis

Assad Abbas, Limin Zhang, Samee U. Khan
2014 World Patent Information  
This literature review presents the state-of-the-art in patent analysis and also presents taxonomy of patent analysis techniques.  ...  The rapid growth of patent documents has called for the development of sophisticated patent analysis tools.  ...  networks.  ... 
doi:10.1016/j.wpi.2013.12.006 fatcat:prs6spbuhfd6lheiocbw5jz3di

Getting Patents and Economic Data to Speak to Each Other: An 'Algorithmic Links with Probabilities' Approach for Joint Analyses of Patenting and Economic Activity

Travis J. Lybbert, Nikolas Jason Zolas
2012 Social Science Research Network  
We conclude with a discussion on some of the possible applications of the concordance and provide a sample analysis that uses our preferred ALP concordance to analyze international patent flows based on  ...  Based on these comparisons, we select a preferred ALP approach and discuss advantages of this approach relative to conventional approaches.  ...  Linking patent and economic data at this aggregate level is based simply on the country-year unit of analysis and has enabled research on questions such as measuring the rate of innovation (Porter and  ... 
doi:10.2139/ssrn.2161982 fatcat:qcy62khwpjh4pjevk6g6af3dhy
« Previous Showing results 1 — 15 out of 14,912 results