Development of Novel Patent Classification Framework by Exploiting Semantic Deep Learner

Patents are an essential information source used to monitor, track, and analyze nanotechnology. When it comes to search nanotechnology-related patents, a keyword search is often incomplete and struggles to cover such an interdisciplinary discipline. Patent classification schemes can reveal far better results since they are assigned by experts who classify the patent documents according to their technology. In this paper, we present the most important classifications to search nanotechnology patents and analyze how nanotechnology is covered in the main patent classification systems used in search systems nowadays: the International Patent Classification (IPC), the United States Patent Classification (USPC), and the Cooperative Patent Classification (CPC). We conclude that nanotechnology has a significantly better patent coverage in the CPC since considerable more nanotechnology documents were retrieved than by using other classifications, and thus, recommend its use for all professionals involved in nanotechnology patent searches.

The Mirror method, which has been proposed as a new business exploration method, was evaluated for its effectiveness in a different case study than the previous study. Specifically, we applied the Mirror method to Ajinomoto’s new business in the 2010s, “Amino Index,” which evaluates disease risk from blood samples, and confirmed its effectiveness. We also evaluated whether the Mirror method would work effectively when only the International Patent Classification (IPC) was used, instead of using the Japanese Patent Classifications (FI, theme code, and F-term) independently assigned by the Japan Patent Office, which are assumed in the Mirror method. As a result, we confirmed that the Mirror method cannot extract appropriate new uses when only the IPC is used.

The current classification of patent data that refers to the IPC (International Patent Classification) of the WIPO (World Intellectual Property Organization), deemed not reflect the classification of the field of ICT (Information & Communication Technology). ICT applications are usually included in sections G (Physics) and H (Electricity). This paper will evaluate the eight groupings of patents based on the IPC classes (G01, G06, G09, G11, H01, H03, H04, and H06) of patents registered in the Directorate General of Intellectual Property Rights in Indonesia, from the year 1991 to 2000. The algorithm used to grouping is KMeans, KMeans++, Hierchical Clustering, and a combination of these three algorithms with SVD (Singular Value Decomposition). For external validation, Purity and F-Measure are used, whereas Silhouette is used for internal validation. From the experimental results it can be concluded that SVD provides improvements to the clustering results. In addition, the use of abstract does not necessarily improve the performance of clustering, and the use of phrase does not always yield better cluster than the use of the word as index. Moreover, no cluster has purity measure greater than 50%, which means that the existing IPC classification has not been able to accommodate the field of ICT appropriately.

Patent Classification Reform: Implications for Teaching, Learning and Using the Patent LiteraturePatents are one of the core literatures of engineering. Academic engineering librarians oftenprovide formal and informal instruction to students on how to search the patent literature,including how to use patent classification codes to retrieve patents related to specifictechnologies. The major patent classification systems in use today include the InternationalPatent Classification (IPC), the European Classification (ECLA), and the U.S. PatentClassification (USPC). In early 2011 the European Patent Office (EPO) and U.S. Patent andTrademark Office (USPTO) announced a project to create a joint classification system called theCooperative Patent Classification (CPC). The CPC will be based on ECLA and the IPC andincorporate the best classification practices from the USPTO. Starting in 2013 the EPO andUSPTO will classify all their documents using the CPC. This paper will explore how the CPCwill be implemented in patent databases and its potential impacts on how engineering librariansteach students to use the patent literature. The author will describe the organization of the CPCand its relationship to current classification systems. The paper will also review teachingmaterials and resources for learning about the CPC.

QuantNet is an integrated web-based environment consisting of different types of statistics-related documents and program codes. Its goal is creating reproducibility and offering a platform for sharing validated knowledge native to the social web. To increase the information retrieval (IR) efficiency there is a need for incorporating semantic information. Three text mining models will be examined: vector space model (VSM), generalized VSM (GVSM) and latent semantic analysis (LSA). The LSA has been successfully used for IR purposes as a technique for capturing semantic relations between terms and inserting them into the similarity measure between documents. Our results show that different model configurations allow adapted similarity-based document clustering and knowledge discovery. In particular, different LSA configurations together with hierarchical clustering reveal good results under M3 evaluation. QuantNet and the corresponding Data-Driven Documents (D3) based visualization can be found and applied under quantlet. The driving technology behind it is Q3-D3-LSA, which is the combination of “GitHub API based QuantNet Mining infrastructure in R”, LSA and D3 implementation.

An improved focused crawler based on Semantic Similarity Vector Space Model

The International Patent Classification (IPC) is used for the classification of patents according to their technological area. Research on the IPC automatic classification system has focused on applying various existing machine learning methods rather than considering the data characteristics or the field structure of the patent documents. This paper proposes a new method for IPC automatic classification using two structural fields, the technical field and the background field selected by applying the characteristics of patent documents. The effects of the structural fields of the patent document classification are examined using a multi-label model and 564,793 registered patents of Korea at the IPC subclass level. An 87.2% precision rate is obtained when using titles, abstracts, claims, technical fields and backgrounds. From this sequence, it is verified that the technical field and background field play an important role in improving the precision of IPC multi-label classification at the IPC subclass level.

The Cooperative Patent Classifications (CPC) recently developed cooperatively by the European and US Patent Offices provide a new basis for mapping patents and portfolio analysis. CPC replaces International Patent Classifications (IPC) of the World Intellectual Property Organization. In this study, we update our routines previously based on IPC for CPC and use the occasion for rethinking various parameter choices. The new maps are significantly different from the previous ones, although this may not always be obvious on visual inspection. We provide nested maps online and a routine for generating portfolio overlays on the maps; a new tool is provided for “difference maps” between patent portfolios of organizations or firms. This is illustrated by comparing the portfolios of patents granted to two competing firms—Novartis and MSD—in 2016. Furthermore, the data is organized for the purpose of statistical analysis.

The international patent classification as a search tool

The discovery of knowledge from large-scale text data or semi-structured data is very difficult. In text mining, useful information is extracted out of such large text corpus which fulfills a user current information need. This process is being exploited by various organizations for quality improvement, business need, and understanding user behavior. The text available in unstructured and semi-structured form can come through sources such as medical, financial, market, scientific, and others documents. Text mining applies quantitative approach to analyze massive amount of textual data and tries to solve information overload problem. The main objective is to review text mining techniques, application areas, and existing issues.

This paper presents a performance analysis and comparison of several pre-processing methods used in automatic patent classification with graph kernels for Support Vector Machine (SVM). The pre-processing methods are based on the data transform techniques, namely data scaling, data centering, data standardization, data normalization, the Box-Cox transform and the Yeo-Johnson transform. The automatic patent classification is designed to classify an input of patent citation graphs into one of 10 possible classes of the International Patent Classification (IPC). The input is taken with various background conditions. The experiments showed that the best result is achieved when the pre-processing method is data normalization, achieving a classification accuracy of up to 85.33.15% for the KEHL and 93.80% for the KVHL. In contrast, for the KEHG, the preprocessing method application decreased the accuracy.

For information retrieval and text-mining, a robust scalable framework is required to represent the information extracted from documents and enable visualization and query of such information. One very widely used model is the vector space model which is based on the bag-of-words approach. However, it suffers from the fact that it loses important information about the original text, such as information about the order of the terms in the text or about the frontiers between sentences or paragraphs. In this paper, we propose a graph-based text representation, which is capable of capturing (i) Term order (ii) Term frequency (iii) Term co-occurrence (iv) Term context in documents. We also apply the graph model into our text mining task, which is to discover unapparent associations between two and more concepts (e.g. individuals) from a large text corpus. Counterterrorism corpus is used to evaluate the performance of various retrieval models, which demonstrates feasibility and effectiveness of graphic text representation in information retrieval and text mining.

Report on the fourth session of ad hoc IPC Reform Working Group, Geneva, 30 October–3 November 2000

There exist noisy, unparallel sentences in parallel web pages. Web page structure is subjected to some limitation for sentences alignment task for web page text. The most straightforward way of aligning sentences is using a translation lexicon. However, a major obstacle to this approach is the lack of dictionary for training. This paper presents a method for automatically align Mongolian-Chinese parallel text on the Web via vector space model. Vector space model is an algebraic model for representing any object as vectors of identifiers, such as index terms. In the statistically based vector-space model, a sentence is conceptually represented by a vector of keywords extracted from the text. Extracted keywords are composed by content words, known as terms and the weight of a term in a sentence vector can be determined tf-idf method. CHI is used to compute the association between bilingual words. Once the term weights are determined, the similarity between sentence vectors is computed via cosine measure. The experimental results indicate that the method is accurate and efficient enough to apply without human intervention.

Huge digital data is typical nowadays. Consequently, text clustering has become a crucial text mining technique nowadays. Organizing search information into groups (or clusters) not only makes the search results more meaningful, but makes the system more efficient since the user views only the relevant information and ignores the rest. An example is clustering web search engine result into meaningful results. Many text clustering approaches and their corresponding algorithms exist, but none has been found to be sufficient. There is also insufficient understanding of the algorithms as well as lack of agreed formal classification of the algorithms. There is thus, need for an in-depth study of the various algorithms. In this paper, we describe the Vector Space Model (VSM) method of text representation. We also give an overview of the text clustering approaches that apply the VSM .These include distance based approach, feature extraction approach, density-based approach, grid-based approach, and neural networks approach. We describe the characteristics of each accompanied by a representative algorithm. The paper thus informs researchers of text mining concerning the current state of affairs of text clustering algorithm. Keywords: clusters, text clustering, text mining, vector space model.