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

Aristodemou, Leonidas; Tietze, Frank

doi:10.1016/j.wpi.2018.07.002

Cited by 151 publications

(58 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Beyond purely quantitative patent statistics, qualitative parameters are increasingly used to generate meaningful patent landscapes [9][10][11][12]. The software PatentSight used in the present study [2][3][4] is one of several tools on the market, which combine enhanced patent databases with an advanced quality analysis software [9][10][11]13].…”

Section: Discussionmentioning

confidence: 99%

“…However, each of these sets still comprises 10,000 of patent families each. Smaller, more homogeneous clusters of high value patents could be identified within sets, requiring further drilling, by exploring lower classification levels, or by means of keyword filters or artificial intelligence tools, such as semantic analysis or text mining [11,12].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

International Collaboration Generates High Quality Clusters of Pharmaceutical Patents

2019

View full text Add to dashboard Cite

The worldwide active patent portfolio has nearly doubled in numbers and strength since 2000. The number of active pharmaceutical patent families has tripled in the same time period. The quantitative growth results mostly from a surge of patents from China, half of them classified in A61K36 (‘medicinal preparations of undetermined constitution containing material from algae, lichens, fungi or plants’). High-quality patents exhibit a slower growth curve, and cluster within the three areas biologicals; heterocyclic compounds, and cancer drugs. However, the highest concentration of high-quality patents was found when selecting patents listing inventors from at least two out of the five most important countries of origin for pharmaceutical patents: China, EP countries, Japan, South Korea and the USA.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

International Collaboration Generates High Quality Clusters of Pharmaceutical Patents

2019

View full text Add to dashboard Cite

show abstract

“…Besides this, the authors defined four key fields of application of patent-analytical studies. They are: knowledge management (including classification and patent quality evaluation), technology management (revealing technology trends and forecast of development of certain technology areas), IP economic value (including the issues of high-tech companies' performance, patent value estimation and defining the amount of loss inflicted by patent infringements, as well as macroeconomic forecast issues), data management (including mainly patent digitising, provisioning of patent information databases and improvement of searching algorithms) [6].…”

Section: Current Status Of Research On Public Sector Entities' Ip Bamentioning

confidence: 99%

Review of Methods and Tools for Intellectual Property Analysis of Public Sector Entities

Khomenko

2020

КФ

View full text Add to dashboard Cite

The low efficiency of intellectual property (IP) in the public sector in our current economic environment is largely due to the insufficient development of the prevailing accounting and analytical system. Analytical methods, and the information basis of their application, are the core of this system. The formation of an accounting and analytical system consistent with the development priorities of public sector entities requires special research.This article provides a review of the methods and tools of analysis used by Russian and foreign scientists in the field of IP. Our research sample comprises 52 foreign and 39 Russian sources. Through a detailed textual analysis process, we systematise the existing methods used in the analyses of certain aspects of intellectual activity, and assess the information disclosure therein. Our evaluation is targeted towards identifying prospects for harmonising Russian and international approaches, and provide the groundwork for the improvement of accounting and analytical support for IP management in the public sector.Our results reveal possibilities for expanding the system of IP analysis methods for solving problems in the field of the IP economics and management on the basis of patent analytics. We also collate and classify patent analytics methods, and identify existing methodological problems at the macro- and microeconomic levels. Analytical methods are grouped in accordance with three stages of the reciprocal model of IP accounting and analysis in the public sector, developed within the framework of a novel theoretical and methodological approach.In conclusion, we illustrate the potential for applying the methods of nonlinear dynamics and the dynamic theory of innovation (re: patent information) to determine the trajectories of public sector entity development concerning levels of information disclosure. We also identify areas for follow up research revealed through our analysis.

show abstract

“…As for the applications of machine learning to intellectual property, in [ 24 ], they reviewed 57 papers on artificial intelligence, automatic and in-depth learning associated with intellectual property. In [ 25 ], the employed algorithms were Support Vector Machines, Neural Networks and Decision Trees.…”

Section: Literature Reviewmentioning

confidence: 99%

Use of the Industrial Property System in Colombia (2018): A Supervised Learning Application

Lis-Gutiérrez

Torres

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The purpose of this paper is to establish ways to predict the spatial distribution of the use of the intellectual property system from information on industrial property applications and grants (distinctive signs and new creations) and copyright registrations in 2018. This will be done using supervised learning algorithms applied to information on industrial property applications and grants (trademarks and new creations) and copyright registrations in 2018. Within the findings, 4 algorithms were identified with a level of explanation higher than 80%: (i) Linear Regression, with an elastic network regularization; (ii) Stochastic Gradient Descent, with Hinge loss function, Ringe regularization (L2) and a constant learning rate; (iii) Neural Networks, with 1,000 layers, with Adam’s solution algorithm and 2,000 iterations; (iv) Random Forest, with 10 trees.

show abstract

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

Cited by 151 publications

References 64 publications

International Collaboration Generates High Quality Clusters of Pharmaceutical Patents

International Collaboration Generates High Quality Clusters of Pharmaceutical Patents

Review of Methods and Tools for Intellectual Property Analysis of Public Sector Entities

Use of the Industrial Property System in Colombia (2018): A Supervised Learning Application

Contact Info

Product

Resources

About