A patent quality analysis and classification system using self-organizing maps with support vector machine

Wu, Jheng-Long; Chang, Pei‐Chann; Tsao, Cheng-Chin; Fan, Chin-Yuan

doi:10.1016/j.asoc.2016.01.020

Cited by 77 publications

(38 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies develop many types of patent indexes focusing on the value of the patent [34], patent quality [35], patent citations [36] and patent novelty [37]. Thus, future research should develop the decomposition framework to address these patent indexes to clarify corporate priority changes.…”

Section: Discussionmentioning

confidence: 99%

Research and Development Strategy in Biological Technologies: A Patent Data Analysis of Japanese Manufacturing Firms

2016

View full text Add to dashboard Cite

Biological technology allows us to invent new medical approaches, create effective food production methods and reserves and develop new materials for industrial production. There is a diversity of biological technology types, and different technologies have different priorities for invention. This study examines the factors that are important for the invention of biology-related technologies in Japan using patent application data and a decomposition analysis framework. As the results show, patent applications related to biochemistry and biotechnology increased until 1995 because of the expanded scale of R&D activities and the high priority assigned to biological technology. However, the number of patent applications stagnated after 1995, because the importance of biochemistry, especially waste-gas treatment technologies, decreased. Additionally, patent applications for medicines and disease-related technologies increased rapidly from 1971 to 1995. The primary determinant of rapid growth is an increase in research priority, especially among firms in the chemical industry whose technologies are related to supplemental foods and foods with health-promoting benefits. Finally, patent applications involving foodstuff-and agriculture-related technologies increased from 1971 to 1995 due to increased R&D and the increased priority of biological technology.

show abstract

Section: Discussionmentioning

confidence: 99%

Research and Development Strategy in Biological Technologies: A Patent Data Analysis of Japanese Manufacturing Firms

2016

View full text Add to dashboard Cite

show abstract

“…Finally, based on the structured data, the big data learning approaches including classification, regression, and clustering, etc., are used for various purposes, such as patent novelty detection and identifying patent quality, trend analysis and technology forecasting, managing R&D planning, etc.. The visual output of the patent data can be represented in the form of graphs, networks and patent maps [15], [16].…”

Section: Introductionmentioning

confidence: 99%

Patent Analytics Based on Feature Vector Space Model: A Case of IoT

Lei

Zheng

2019

IEEE Access

View full text Add to dashboard Cite

The number of approved patents worldwide increases rapidly each year, which requires new patent analytics to efficiently mine the valuable information attached to these patents. Vector space model (VSM) represents documents as high-dimensional vectors, where each dimension corresponds to a unique term. While originally proposed for information retrieval systems, VSM has also seen wide applications in patent analytics, and used as a fundamental tool to map patent documents to structured data. However, VSM method suffers from several limitations when applied to patent analysis tasks, such as loss of sentence-level semantics and curse-of-dimensionality problems. In order to address the above limitations, we propose a patent analytics based on feature vector space model (FVSM), where the FVSM is constructed by mapping patent documents to feature vectors extracted by convolutional neural networks (CNN). The applications of FVSM for three typical patent analysis tasks, i.e., patents similarity comparison, patent clustering, and patent map generation are discussed. A case study using patents related to Internet of Things (IoT) technology is illustrated to demonstrate the performance and effectiveness of FVSM. The proposed FVSM can be adopted by other patent analysis studies to replace VSM, based on which various big data learning tasks can be performed.

show abstract

“…Both the proposed DSOM and DNSFLA have a wide range of real application scenarios. For reference, the rudiment example of formulas included in the DSOM algorithm can be found in [45,46], and the rudiment example of formulas included in the DNSFLA algorithm can be found in [47,48]. To make it easier to follow the formulas proposed in this section, we still take the application of Smart Home described in reference [37] as an example.…”

Section: Analysis Of Msdgasmentioning

confidence: 99%

Multistage Dynamic Packet Access Mechanism of Internet of Things

Meng

Chen

Zhang

2018

Mobile Information Systems

View full text Add to dashboard Cite

In the scenario of mass control commands requesting for network access, confined by the best-effort network service mode, it is easy to bring about resource competition and thus a phenomenon of access failure on major and urgent service request at the data access center for the Internet of ings. In this event, the dynamic diversification of control command is unable to access the necessary resources on a comparatively fair basis, causing low efficiency in heterogeneous resource utilization at the access center. is paper defines the problem of group request dynamic resource allocation and further converts it into the problem of 0-1 integer and linear programming and proposes a multistage dynamic packet access strategy. is strategy works first on dynamic group division on the users' mass control requests using the high ability of self-organizing feature maps and then searches for the optimized matching resources based on the frog-leaping algorithm which has a better capacity for global searching for the best resources. is paper analyzes the feasibility of this strategy and its astringency. e experimental results demonstrate that the strategy can effectively improve the success rate of access to the data center for the Internet of ings and reduce network blockage and response delay.

show abstract

A patent quality analysis and classification system using self-organizing maps with support vector machine

Cited by 77 publications

References 32 publications

Research and Development Strategy in Biological Technologies: A Patent Data Analysis of Japanese Manufacturing Firms

Research and Development Strategy in Biological Technologies: A Patent Data Analysis of Japanese Manufacturing Firms

Patent Analytics Based on Feature Vector Space Model: A Case of IoT

Multistage Dynamic Packet Access Mechanism of Internet of Things

Contact Info

Product

Resources

About