Pemodelan topik pada dokumen paten terkait pupuk di Indonesia berbasis Latent Dirichlet Allocation

Introduction. Fertilizer is one of the most important production factors in the world of agriculture. It is crucial to increase the capacity of technology related to fertilizers. Analysis of patent documents can be one way to analyze technological developments, especially fertilizers. Data Collection Methods. The data used in this research are metadata, especially the title and abstract of a patent document in Indonesia. With the keyword "fertilizer," Patent metadata was processed in the 1945-2017 period. Data Analysis. The LDA model can provide a reasonable interpretation regarding topic modeling based on text data. Results and Discussion. The results find that degree of the patent title is better than the abstract of the patent. The LDA approach can adequately separate the topics of fertilizer patent technology so that it does not have multiple interpretations. Conclusion. Based on the findings, there are nine essential topics in the development of fertilizer technology. There is a phenomenon of the lack of technology collaboration between IPC technology sections.

Engineering Knowledge Graph from Patent Database

We propose a large scalable engineering knowledge base as an integrated knowledge graph, comprising sets of (entity, relationship, entity) triples that are real-world engineering ‘facts’ found in the patent database. We apply a set of rules based on the syntactic and lexical properties of claims in a patent document to extract entities and their associated relationships that are supposedly meaningful from an engineering design perspective. Such a knowledge base is expected to support inferencing, reasoning, recalling in various engineering design tasks. The knowledge base has a greater size and coverage in comparison with the previously used knowledge bases in the engineering design literature.

MEXN: Multi-Stage Extraction Network for Patent Document Classification

The patent document has different content for each paragraph, and the length of the document is also very long. Moreover, patent documents are classified hierarchically as multi-labels. Many works have employed deep neural architectures to classify the patent documents. Traditional document classification methods have not well represented the characteristics of entire patent document contents because they usually require a fixed input length. To address this issue, we propose a neural network-based document classification for patent documents by designing a novel multi-stage feature extraction network (MEXN), which comprise of paragraphs encoder and summarizer for all paragraphs. MEXN features analysis of the whole documents hierarchically and providing multi-labels outputs. Furthermore, MEXN preserves computing performance marginally increase. We demonstrate that the proposed method outperforms current state-of-the-art models in patent document classification tasks with multi-label classification experiments for USPD datasets.

Drafting Assistance On Traditional Jamu UMKM

Patent Drafting is a method for preparing patent documents. As it is known, UMKM Jamu is engaged in the health sector by producing traditional herbal medicine which is believed to be effective in preventing the growth of cancer cells and various other diseases. UMKM located in Wonorejo Village, Lumajang Regency, need patent drafting assistance for the preparation of patent documents. Therefore, this assistance is carried out with the aim of providing understanding to the UMKM Jamu Ibuk producers regarding patents. The output of this activity is a patent document ready to register. With this activity, it is hoped that it can provide thoughts on the importance of protecting Intellectual Property for MSMEs and the wider community.

Technological Prospection of Oil Nanoparticles: Primary Characteristics and Profiles

Background: The search for technological applications for oils has been growing, largely due to their potential nutritional and economic applications. Encapsulation makes it possible to reduce the disadvantages of oils, such as physical instability or thermodynamics, or to improve their technological properties, enabling their use in various industrial areas. Nanoencapsulated oils have the potential to improve oil bioavailability and achieve controlled release and are able to target bioactive compounds with greater precision than microencapsulated oils. Objective: The present study aims to evaluate the primary characteristics and profiles of the technological prospection of oil nanoparticles. Results: Exponential growth in patent filing was noted with a peak in 2017, with China filing the highest numbers of patents. Regarding the area of application, the food industry was most common followed by the pharmaceutical industry. The most commonly used terms in patent documents on the subject were nanoemulsion and nanoparticle. The most commonly used oil, technique, wall materials and emulsifiers were soybean oil; emulsification; chitosan and lecithin; and Span 80, Tween 80 and Tween 40, respectively. The obtained articles were typically patent documents. The main depositor was Jiangnan University, and most inventors filed the same number of patent documents. Conclusion: Nanoencapsulation of oils has many known advantages that have been widely published in the literature and used by industry. There is a trend in the growth of patent document deposits and related scientific publications, indicating that many innovations have been made and highlighting the importance of oil nanoencapsulation.

Idea Generation and New Direction for Exploitation Technologies of Coal-Seam Gas through Recombinative Innovation and Patent Analysis

Coal-seam gas (CSG), as an alternative energy, has the characteristics of resource scarcity and technological exploitation complexity. The generation of ideas is vital to develop more efficient exploitation technologies for CSG. Innovative ideas originate from the recombination of existing knowledge elements according to recombinative innovation. The previous literature has focused on exploring an abundance of combinations, which leads to blindness towards idea generation. For this reason, it is critical to search for more valuable matching patterns among the redundant combinations of elements. In line with this concept, this paper proposes a method that consists of three phases: the collection of knowledge elements, the analysis of knowledge element depth and diversity, and the analysis of knowledge element relationships. In this process, we take the patent document as the carrier of knowledge recombination and identify the optimization method in the reorganization process by means of latent Dirichlet allocation (LDA) and association rules. This method is expected to assist in sparking better ideas for CSG exploitation technologies.