Empirical study of constructing a knowledge organization system of patent documents using topic modeling

A knowledge organization system (KOS) can help easily indicate the deep knowledge structure of a patent document set. Compared to classification code systems, a personalized KOS made up of topics can represent the technology information in a more agile, detailed manner. This paper presents an approach to automatically construct a KOS of patent documents based on term clumping, Latent Dirichlet Allocation (LDA) model, K-Means clustering and Principal Components Analysis (PCA). Term clumping is adopted to generate a better bag-of-words for topic modeling and LDA model is applied to generate raw topics. Then by iteratively using K-Means clustering and PCA on the document set and topics matrix, we generated new upper topics and computed the relationships between topics to construct a KOS. Finally, documents are mapped to the KOS. The nodes of the KOS are topics which are represented by terms and their weights and the leaves are patent documents. We evaluated the approach with a set of Large Aperture Optical Elements (LAOE) patent documents as an empirical study and constructed the LAOE KOS. The method used discovered the deep semantic relationships between the topics and helped better describe the technology themes of LAOE. Based on the KOS, two types of applications were implemented: the automatic classification of patents documents and the categorical refinements above search results.     

Exploring the feasibility and accuracy of Latent Semantic Analysis based text mining techniques to detect similarity between patent documents and scientific publications

In this study, we examine and validate the use of existing text mining techniques (based on the vector space model and latent semantic indexing) to detect similarities between patent documents and scientific publications. Clearly, experts involved in domain studies would benefit from techniques that allow similarity to be detected—and hence facilitate mapping, categorization and classification efforts. In addition, given current debates on the relevance and appropriateness of academic patenting, the ability to assess content-relatedness between sets of documents—in this case, patents and publications—might become relevant and useful. We list several options available to arrive at content based similarity measures. Different options of a vector space model and latent semantic indexing approach have been selected and applied to the publications and patents of a sample of academic inventors (n = 6). We also validated the outcomes by using independently obtained validation scores of human raters. While we conclude that text mining techniques can be valuable for detecting similarities between patents and publications, our findings also indicate that the various options available to arrive at similarity measures vary considerably in terms of accuracy: some generally accepted text mining options, like dimensionality reduction and LSA, do not yield the best results when working with smaller document sets. Implications and directions for further research are discussed.     

Patent information retrieval: approaching a method and analysing nanotechnology patent collaborations

Many challenges still remain in the processing of explicit technological knowledge documents such as patents. Given the limitations and drawbacks of the existing approaches, this research sets out to develop an improved method for searching patent databases and extracting patent information to increase the efficiency and reliability of nanotechnology patent information retrieval process and to empirically analyse patent collaboration. A tech-mining method was applied and the subsequent analysis was performed using Thomson data analyser software. The findings show that nations such as Korea and Japan are highly collaborative in sharing technological knowledge across academic and corporate organisations within their national boundaries, and China presents, in some cases, a great illustration of effective patent collaboration and co-inventorship. This study also analyses key patent strengths by country, organisation and technology.     

Significant difference of dependence upon scientific knowledge among different technologies

Summary The authors have constructed an original database of the full text of the Japanese Patent Gazette published since 1994. The database includes not only the front page but also the body text of more than 880,000 granted Japanese patents. By reading the full texts of all 1,500 patent samples, we found that some inventors cite many academic papers in addition to earlier patents in the body texts of their Japanese patents. Using manually extracted academic paper citations and patent citations as “right” answers, we fine-tuned a search algorithm that automatically retrieves cited scientific papers and patents from the entire texts of all the Japanese patents in the database. An academic paper citation in a patent text indicates that the inventor used scientific knowledge in the cited paper when he/she invented the idea codified in the citing patent. The degree of science linkage, as measured by the number of research papers cited in patent documents, is particularly strong in biotechnology. Among other types of technology, those related to photographic-sensitized material, cryptography, optical computing, and speech recognition also show strong science linkage. This suggests that the degree of dependence on scientific knowledge differs from technology to technology and therefore, different ways of university-industry collaboration are necessary for different technology fields.     

Automation of patent classification

The current use, and potential for expansion, of automated classification methods in the USPTO is described. Typical applications are in (1) assigning new patent applications to the group of examiners most appropriate for the area of technology for each application, (2) classification of new documents into the search files, and (3) reclassification of patent specifications. Another benefit is the retrieval of ranked listings of relevant prior art. The author opines that the use and development of such systems are likely to become increasingly important in handling large volumes of patent documents.     

The GET command: A powerful new patent searching tool from Pergamon infoline

The use of Pergamon InfoLine's GET command for the enhancement of online patent searching on the PATSEARCH^R, INPADOC and INPANEW data-bases is described. GET uniquely provides patent searchers with the capability to perform statistical analyses of search results online, utilizing the power of a host's mainframe computer. With GET, there is no need to have a microcomputer and associated software to analyze search results downloaded from an online host. Applications of GET discussed include: determining classification categories relevant for a patent search; finding key cited references for a technological field; analyzing patent ownership; expanding a search from U.S. patents to non-U.S. patents; and cross file searching.     

Identifying patent infringement using SAO based semantic technological similarities

Companies should investigate possible patent infringement and cope with potential risks because patent litigation may have a tremendous financial impact. An important factor to identify the possibility of patent infringement is the technological similarity among patents, so this paper considered technological similarity as a criterion for judging the possibility of infringement. Technological similarities can be measured by transforming patent documents into abstracted forms which contain specific technological key-findings and structural relationships among technological components in the invention. Although keyword-based technological similarity has been widely adopted for patent analysis related research, it is inadequate for identifying patent infringement because a keyword vector cannot reflect specific technological key-findings and structural relationships among technological components. As a remedy, this paper exploited a subject–action–object (SAO) based semantic technological similarity. An SAO structure explicitly describes the structural relationships among technological components in the patent, and the set of SAO structures is considered to be a detailed picture of the inventor’s expertise, which is the specific key-findings in the patent. Therefore, an SAO based semantic technological similarity can identify patent infringement. Semantic similarity between SAO structures is automatically measured using SAO based semantic similarity measurement method using WordNet, and the technological relationships among patents were mapped onto a 2-dimensional space using multidimensional scaling (MDS). Furthermore, a clustering algorithm is used to automatically suggest possible patent infringement cases, allowing large sets of patents to be handled with minimal effort by human experts. The proposed method will be verified by detecting real patent infringement in prostate cancer treatment technology, and we expect this method to relieve human experts’ work in identifying patent infringement.     

IP portfolios and evolution of biomedical additive manufacturing applications

Additive manufacturing (AM) or 3D printing includes techniques capable of manufacturing regular and irregular shapes for small batches of customized products. The ability to customize unusual shapes makes the process particularly suitable for prosthetic products used in biomedical applications. AM adoption in the field of biomedical applications (called bio-AM in this research) has seen significant growth over the last few years. This research develops an Intellectual Property (IP) analytical methodology to explore the portfolios and evolution of patents, as well as their relevance to Taiwan’s Ministry of Science and Technology (MOST) research projects in bio-AM domain. Specifically, global and domestic IP portfolios for bio-AM innovations are studied using the proposed method. First, the domain documents (of US patents and MOST projects) are collected from a global patent database and MOST project database. The key term frequency counts and technical clustering analysis of the collected documents are derived. The key terms and appearance frequencies in documents form the basis for document clustering and similarity analysis. The ontology of bio-AM is constructed based on the clustering results. Finally, the patents and projects in the adjusted clusters are subject to evolution analysis using concept lattice analysis. This research provides a computer supported IP evolution analysis system, based on the developed algorithms, for the decision support of IP and R&D strategic planning.     

An in-depth empirical analysis of patent citation counts using zero-inflated count data model: The case of KIST

Patent citation counts represent an aspect of patent quality and knowledge flow. Especially, citation data of US patents contain most valuable pieces of the information among other patents. This paper identifies the factors affecting patent citation counts using US patents belonging to Korea Institute of Science and Technology (KIST). For patent citation count model, zero-inflated models are announced to handle the excess zero data. For explanatory factors, research team characteristics, invention-specific characteristics, and geographical domain related characteristics are suggested. As results, the size of invention and the degree of dependence upon Japanese technological domain significantly affect patent citation counts of KIST.     

Blockchain patent landscaping: An expert based methodology and search query

The present study is concerned with the emergence of Blockchain related technologies in terms of patenting activity. Blockchain has captured the attention of the public and research has intensified in this field over the last few years, making it a highly interesting topic of study for a patent analysis in order to obtain insight into the developments of this emerging technology. In this paper we present a unique methodology and exhaustive search strategy for identifying Blockchain patent documents by using a combination of specific keywords and patent classifications. This query was built in cooperation with subject matter experts of the European Patent Office (EPO). Our keyword set was then analysed by relevance and was prioritised. The set of specific relevant patent classifications was furthermore combined with keywords in order to exclude false positives. With our methodology we present an exhaustive query for retrieving a highly relevant dataset of Blockchain related patents, extracted from the EPO databases that can be used for patent landscaping exercises or any other bibliometric analysis. In a case study we applied the search strategy to analyse worldwide Blockchain patenting from 2008 till 2018. The results are presented in this paper.     

知识视角下设计驱动的颠覆式创新方法研究

目的 颠覆式创新是企业实现跨越式追赶的重要路径,针对当前识别颠覆式创新机会的不足,基于知识基因与深度学习协同优化,提出设计驱动的颠覆式创新早期识别方法。方法 梳理知识视角下设计驱动的颠覆式创新流程,针对创新模糊前端阶段并基于“产品知识基因”的概念,首先通过大数据文本分析方法洞察用户未来需求,进行产品意义重构;其次对相关领域专利数据进行“主语—行为—宾语”结构与“技术—关系—技术”结构语义分析并建立产品知识库;最后在此基础上类比基因工程思维模式重组技术方案,寻求产品颠覆式创新。结论 以未来空调为设计研究对象,验证研究方法的可行性与有效性,能够帮助企业识别颠覆式创新设计机会,对优化资源配置和规划设计战略具有现实指导价值。     

基于AHP-TRIZ的智能婴儿床专利规避创新设计

目的 为了解决目前国内智能婴儿床产品所存在的功能需求单一、设计结构不合理、实用性不强等问题,提出了基于用户需求的层次分析法(AHP)和发明问题解决理论(TRIZ)相结合的智能婴儿床专利规避创新设计研究。方法 首先通过对现有婴儿床产品的调研归类和对目标用户进行的市场调研,分析总结了智能婴儿床的产品机会缺口;其次,采用AHP法进行用户需求权重等级评定,将需求权重项转化为技术需求点,同时在专利检索数据库中进行查阅,对技术需求点相关的目标专利进行分析;最后,运用TRIZ理论分析目标专利中出现的矛盾问题,并将这些问题转化为相应的技术,形成矛盾矩阵,再通过发明原理解决矛盾,该设计应用的相关原理主要为抽取原理、空间维数变化原理、机械系统代替原理和气压与液压结构原理,并使用Rhino等三维建模软件输出智能婴儿床产品的概念设计方案。结论 通过将AHP分析法和TRIZ理论相结合的方式,进行了专利规避的创新设计,实现了对育婴人群需求点的客观把握,完成了智能婴儿床产品的专利规避创新设计,验证了AHP-TRIZ理论使用的科学性与准确性。     

Discovery of factors influencing patent value based on machine learning in patents in the field of nanotechnology

Patents represent the technological or inventive activity and output across different fields, regions, and time. The analysis of information from patents could be used to help focus efforts in research and the economy; however, the roles of the factors that can be extracted from patent records are still not entirely understood. To better understand the impact of these factors on patent value, machine learning techniques such as feature selection and classification are used to analyze patents in a sample industry, nanotechnology. Each nanotechnology patent was represented by a comprehensive set of numerical features that describe inventors, assignees, patent classification, and outgoing references. After careful design that included selection of the most relevant features, selection and optimization of the accuracy of classification models that aimed at finding most valuable (top-performing) patents, we used the generated models to analyze which factors allow to differentiate between the top-performing and the remaining nanotechnology patents. A few interesting findings surface as important such as the past performance of inventors and assignees, and the count of referenced patents.     

Exploring 4G patent and litigation informatics in the mobile telecommunications industry

Patent informatics are often analysed for IP protections, particularly in high-tech industries. This research develops a computer-supported generic methodology for discovering evolutions and linkages between litigations and disputed patents. The IP litigations in mobile telecommunications are used as the case study. An ontology framework representing the 4G domain knowledge is defined first. Then, a modified formal concept analysis (MFCA) approach is developed to discover the evolutionary linkages of legal cases and their disputed patents. In addition to citation-based patent analysis, this research provides a new approach in identifying legal and technical evolutions for future R&D planning and IP strategies.     

A new instrument for technology monitoring: novelty in patents measured by semantic patent analysis

Given that in terms of technology novel inventions are crucial factors for companies; this article contributes to the identification of inventions of high novelty in patent data. As companies are confronted with an information overflow, and having patents reviewed by experts is a time-consuming task, we introduce a new approach to the identification of inventions of high novelty: a specific form of semantic patent analysis. Subsequent to the introduction of the concept of novelty in patents, the classical method of semantic patent analysis will be adapted to support novelty measurement. By means of a case study from the automotive industry, we corroborate that semantic patent analysis is able to outperform available methods for the identification of inventions of high novelty. Accordingly, semantic patent information possesses the potential to enhance technology monitoring while reducing both costs and uncertainty in the identification of inventions of high novelty.     

A guide to efficient keyword, sequence and classification search strategies for biopharmaceutical drug-centric patent landscape searches - A human recombinant insulin patent landscape case study

Searching biopharmaceutical drug-related patent information is generally considered to be challenging. In particular, setting up efficient search strategies for comprehensive retrieval of high amounts of patent documents related to processes and methods of use, that achieve a reasonable level of precision, but still remain within a particular search scope. While it is generally accepted that patent information cannot be searched using standardized approaches, it is desirable to have a basic rule set for successful biopharmaceutical drug-related patent information retrieval, particularly facing a steady flow of patent expirations for prominent biologic drugs. The present human recombinant insulin case study shows an assessment of keyword, sequence and classification search strategies for establishing biopharmaceutical drug-centric patent landscapes. The search results of both crude and sophisticated keyword search strategies, as well as of a sequence search strategy, were compared in terms of the key information retrieval quality indicators; the recall and the precision. Through analyses of the relevant retrieved documents, a quality assessment of keyword choice is provided, as well as determining focused IPC and Derwent Manual classification codes and terminology from original patent and Derwent documentation abstract titles. All of which can be used for setting up more efficient search strategies and facilitated document categorization.     

Sources of inspiration? Making sense of scientific references in patents

Scientific references in patent documents can be used as indicators signaling science-technology interactions. Whether they reflect a direct ‘knowledge flow’ from science to technology is subject of debate. Based on 33 interviews with inventors at Belgian firms and knowledge-generating institutes active in nanotechnology, biotechnology and life sciences, we analyze the extent to which scientific references in patents reflect sources of inspiration. Our results indicate that scientific knowledge acts as a source of inspiration for about 50 % of the inventions. At the same time, the scientific references cited in patent documents and available in patent databases do not provide an accurate picture in this respect: 30 % of patents that were inspired by scientific knowledge do not contain any scientific references. Moreover, if scientific references are present, half of them are evaluated as unimportant or background information by the inventor. Overall, these observations provide evidence that scientific references in patent documents signal relatedness with the implied inventions without necessarily implying a direct, inspirational, knowledge flow between both activity realms.     

Academic inventions and patents in the Netherlands: A case study on business sector exploitation

This paper describes a new methodology to identify patent applications based upon research at nine universities and three university medical centers in the Netherlands and a case study elaborating subsequent, scientifically research based, IP exploitation in several sectors. We address the identification and utilization of the intellectual property by domestic business enterprises and start ups based upon patents from university research. A sophisticated semi-automated data collection heuristic was adopted to identify all relevant university-invented patent applications that were filed between 2000 and 2010.In total 2898 patent applications based upon scientific research at universities and related to university inventions were identified. For 952 of these university inventions patent applications were filed by the universities themselves. The total number of university based related patent applications represent 5% of the total volume of patent applications from Dutch origin.A subsequent survey among companies exploiting university research based IP, was carried out to gather information on their actual use of their IP in terms of manpower involved in product or market development and estimated monetary value of the patents. 78 companies responded to this survey. The main findings reveal that a variety of IP exploitation strategies has been used. Overall, more than 50% of the patents still wait to be used for further development and innovations. The number of jobs created by spin offs from university research institutes is approximately 9500 jobs over a period of 10 years. Average revenues from these patents amounted to € 42,000. Several findings from our small-scale national survey on patent exploitation with regards to use and monetary values are in line with general results from the large-scale European PatVal survey and the APE-INV survey.     

Artificial intelligence for patent prior art searching

This study explored how artificial intelligence (AI) could assist patent examiners as part of the prior art search process. The proof-of-concept allowed experimentation with different AI techniques to suggest search terms, retrieve most relevant documents, rank them and visualise their content. The study suggested that AI is less effective in formulating search queries but can reduce the time and cost of the process of sifting through a large number of patents. The study highlighted the importance of the humanin-the-loop approach and the need for better tools for human-centred decision and performance support in prior art searching.     

Scientific literature cited in USPTO patent documents as indicators for the evaluation and analysis of Spanish scientific research in biomedical disciplines

The use of indicators based on the analysis of the scientific literature cited in patent documents is proposed for the evaluation of biomedical research. A study carried out on several groups of researchers working in universities, public research centers, and hospitals, has shown that an important percentage of Spanish scientists have authored publications that are cited in US patents in the field of Biotechnology. The study and analysis of those cites allows a evaluation of the flow of knowledge generated by the different groups of scientists towards the development of technologies, and to learn on the relationship between the characteristics of the cited publications and the frequency they are cited in the patents. The results obtained avail the use of new indicators based on the cites in patents to perform a more complete evaluation of the published research related with Biotechnology and Biomedicine, both at the level of research institutions and individual scientists.