IPC Prediction of Patent Documents Using Neural Network with Attention for Hierarchical Structure

International patent classifications (IPCs) are assigned to patent documents; however, since the procedure for assigning classifications is manually done by the patent examiner, it takes a lot of time and effort to select some IPCs from about 70,000 IPCs. Hence, some research has been conducted on patent classification with machine learning. However, patent documents are very voluminous, and learning with all the claims (the part describing the content of the patent) as input would run out of the necessary memory. Therefore, most of the existing methods learn by excluding some information, such as using only the first claim as input. In this study, we propose a model that considers the contents of all claims by extracting important information for input. We also propose a new decoder that considers the hierarchical structure of the IPC. Finally, we evaluate the model using an evaluation index that assumes the actual use of IPC selection for patent documents.

Analysis of International Patent Applications for Inventions Like Traditional Herbal Medicines

Numerous applications have been filed for patents based on bio-inventions in the Indian patent office. Although there is not any international patent, there is a system of international patent applications whereby the applicant may designate name of countries where they wish to file application for patents nationally. According to international patent classification, the concern class for such a patent applications is A61K36/00. More particularly, the international class (IC) A61K36/00 relates to medicinal preparations of undetermined constitution containing material from algae, lichens, fungi or plants, or derivatives thereof (e.g., traditional herbal medicines). International applications filings under patent cooperation treaty (PCT) for patent purposes can be accessed at the Patentscope (patent search tool of WIPO). All international patent applications for such TK-based inventions have been accessed online at Patentscope using the classification code A61K36 for this study.

Patents for inventions in the Russian oil and gas sector: an analysis of the knowledge database complexity

The authors have analyzed invention patents in the Russian oil and gas sector (OGS) based on a knowledge database complexity index they designed for this purpose. The index takes into account the subclasses and sections of international patent classification (IPC) used in the patents. It has been demonstrated that opportunities for creating breakthrough technologies and radical innovations mostly arise within giant multinational oil and gas field service companies (e.g. Halliburton, Schlumberger, Baker Hughes). At the same time, Russian oil and service companies are noticeably lagging behind the foreign players and Russian actors in the sphere of science and education. The conducted analysis of the sectoral knowledge database revealed several significant risks for the development of the Russian OGS along the innovative trajectory. The risks (relative to the invention patents) arise from inadequate opportunities for creating breakthrough technologies.

Big Data for Prediction

Technical field of big data for prediction lures the attention of different stakeholders. The reasons are related to the potentials of the big data, which allows for learning from past behavior, discovering patterns and values, and optimizing business processes based on new insights from large databases. However, in order to fully utilize the potentials of big data, its stakeholders need to understand the scope and volume of patenting related to big data usage for prediction. Therefore, this chapter aims to perform an analysis of patenting activities related to big data usage for prediction. This is done by (1) exploring the timeline and geographic distribution of patenting activities, (2) exploring the most active assignees of technical content of interest, (3) detecting the type of the protected technical according to the international patent classification system, and (4) performing text-mining analysis to discover the topics emerging most often in patents' abstracts.

PatentNet: multi-label classification of patent documents using deep learning based language understanding

Patent classification is an expensive and time-consuming task that has conventionally been performed by domain experts. However, the increase in the number of filed patents and the complexity of the documents make the classification task challenging. The text used in patent documents is not always written in a way to efficiently convey knowledge. Moreover, patent classification is a multi-label classification task with a large number of labels, which makes the problem even more complicated. Hence, automating this expensive and laborious task is essential for assisting domain experts in managing patent documents, facilitating reliable search, retrieval, and further patent analysis tasks. Transfer learning and pre-trained language models have recently achieved state-of-the-art results in many Natural Language Processing tasks. In this work, we focus on investigating the effect of fine-tuning the pre-trained language models, namely, BERT, XLNet, RoBERTa, and ELECTRA, for the essential task of multi-label patent classification. We compare these models with the baseline deep-learning approaches used for patent classification. We use various word embeddings to enhance the performance of the baseline models. The publicly available USPTO-2M patent classification benchmark and M-patent datasets are used for conducting experiments. We conclude that fine-tuning the pre-trained language models on the patent text improves the multi-label patent classification performance. Our findings indicate that XLNet performs the best and achieves a new state-of-the-art classification performance with respect to precision, recall, F1 measure, as well as coverage error, and LRAP.

A Methodology for Evaluation and Distribution of Patent Applications to INPI-BR Patent Examiners: A Case Study in the Electricity Field

This paper presents the development of a new methodology for evaluation and distribution of patent applications to the examiners at the Brazilian Patent Office considering a specific technological field, represented by classification of the application according to the International Patent Classification (IPC), and the variables corresponding to the volume of data of the application and its complexity for the examination process. After identifying the most relevant variables, such as the Specific Areas of Expertise (ZAE) of the examiners, a mathematical model was developed, including: (a) application of the principal component analysis (PCA) method; (b) calculation of a General Complexity Ratio (IGC); (c) classification into five classes (very light, light, moderate, heavy and very heavy) according to IGC average ranges and standard deviations; (d) implementation of a logic of distribution, compensating very heavy applications with very light ones, and light applications with heavy ones; and (e) calculation of a Distribution Balancing Ratio (IBD), considering the differences between the samples’ medians. The model was validated using a sample of patent applications including, in addition to the identified variables, the time for substantive examination by the examiner. Then, a correlation analysis of the variables with time and a comparison of the classifications according to the time and the IGC generated by the model were carried out. The results obtained showed a high correlation of the IGC with time, above 80%, as well as correct IGC classes in more than 80% of applications. The model proposed herein suggests that the three main relevant variables are: total number of pages, total number of claims, and total number of claim pages.

Cosmonautics Patent Analytics using Cooperative Patent Classification Hierarchy

Patent research is a sector of entrepreneurship that has long been used to understand both technological and financial trends in STEM industries. Such research provides insight into intellectual capital as it relates to entities, countries, and innovation areas, thus being an important factor in research and development decision-making. Yet, the sheer volume of patents filed in conjunction with unorganized attributes within patent databases creates a challenge for effective patent analysis. With this in mind, we create a patent analytic tool that organizes a specific patent class using CPC, applicant, and time attributes.

Technological prospection: the genus Mikania in therapeutic use

The genus Mikania (Asteraceae) comprises about 450 species of these, 203 are found in Brazil and present several chemical and biological activities. Considering the variety of species and their therapeutic properties, the present study aimed to perform technological prospecting of this genus, since this approach aims to contribute to technological, scientific and innovation research. For this purpose, the patent documents were analyzed, regarding the applicant countries, year of filing and the international classification of patents of the genus Mikania. The search was conducted in the databases World Intellectual Property Organization (WIPO), European Patent Office (EPO) and the National Institute of Industrial Property (INPI) in October 2020, using the descriptor “Mikania”; present in the title and/or abstract in addition, documents that included medicinal approaches were selected. Thus, taking into consideration the filing countries, Japan, Brazil and the United States led the patent deposits, with the first document filed in 1991 and the largest number of applications in the years 2000 and 2010. The data concerning the international patent classification are concentrated in subclass A61K, which deals with preparations for medical, dental or hygienic purposes. These results demonstrated the therapeutic and technological potential of the Mikania species and thus which can be evidenced the potential of this study.

MUTUAL PATENTING TRENDS IN TELECOMMUNICATION FIELD ON THE EXAMPLE OF LEADING WORLD PATENT OFFICES

Приводятся результаты патентного исследования в области инновационных технологий на основе общей патентной статистики в мире и в России. Прослеживается устойчивый рост количества патентных заявок, подаваемых как резидентами, так и нерезидентами, в ведущих странах-лидерах. Представлена стратегия правовой охраны инновационных технических решений в целях обеспечения их продвижения на внешние и внутренние рынки. Анализируется динамика взаимного проникновения интеллектуальной собственности со стороны США, стран Европы и КНР; акцент сделан на долю патентных заявок в области техники электросвязи. В основу патентной статистики положена Международная патентная классификация. Сделан вывод о дисбалансе во взаимном патентовании между китайскими субъектами патентования и патентными ведомствами Европы и США. Констатируется падение как общего количества патентных заявок в Российской Федерации, так и количества заявок, поданных нерезидентами. The article provides the results of patent research in the field of innovative technologies based on worldwide and Russian patent statistics. There is a steady increase in the number of patent applications filed both by residents and non-residents in lead countries. The strategy of legal protection for innovative technical solutions is outlined in order to ensure promotion on external and internal markets. The dynamics of mutual intellectual property infiltration between the USA, Europe, and China is analyzed. The authors focused on the share of patent applications in the field of telecommunications technology. The patent statistics is based on the International Patent Classification. The article concludes that there is an imbalance in mutual patenting between Chinese patent subjects and Patent Offices of Europe and the USA. A drop is noted both in the total number of patent applications in the Russian Federation and in the number of applications submitted by non-residents.