DISERTASI KLASIFIKASI PATEN DENGAN PEMBOBOTAN RINGKASAN MENGGUNAKAN PENDEKATAN MACHINE LEARNING

WIDODO, SLAMET and Ermatita, Ermatita and Stiawan, Deris (2025) DISERTASI KLASIFIKASI PATEN DENGAN PEMBOBOTAN RINGKASAN MENGGUNAKAN PENDEKATAN MACHINE LEARNING. Doctoral thesis, Sriwijaya University.

	Image RAMA_21001_03013622025005_COVER.pdf - Cover Image Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_21001_03013622025005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_21001_03013622025005_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
	Text RAMA_21001_03013622025005_0013096707_0003047905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_21001_03013622025005-0013096707_0003047905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (751kB) | Request a copy
	Text RAMA_21001_03013622025005-0013096707_0003047905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (179kB) | Request a copy
	Text RAMA_21001_03013622025005-0013096707_0003047905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_21001_03013622025005-0013096707_0003047905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_21001_03013622025005_0013096707_0003047905_06_Ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (158kB) | Request a copy
	Text RAMA_21001_03013622025005-0013096707_0003047905_Lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Classification of Patents By Weighting Summary of Use Machine Learning Approach Patents are the exclusive rights of inventors to inventions in the field of technology when they create their own inventions or authorize others to implement their inventions. An invention is an inventor's idea that leads to activities aimed at solving specific problems in the field of technology, either in the form of a product or how to treat or refine it for product development. The issue of the complexity of patent proposals for inventors becomes a very important discussion through the process steps that define the patent engineering domain, the foundation of the invention. invention, patent abstract, complete description of the invention, claim, reference search, and abstract. The problem of redundancy of patent abstracts is to avoid duplication or repeated storage of the same information on the IPC (International Patent Classification) label or patent group in several patent documents. over the Internet, thus storing the same information in multiple layers or tags. The aim of this study is to generate a dataset of Indonesian patents for a machine learning model to predict classes or labels from the input data based on the information provided by the patent data. IPC (International Patent Classification) of the previous training course. The primary objective is to identify patterns or relationships in the data that can be used to classify proposed new patent data into one of several predefined IPC-related patent data types. . The model's prediction results can be one, two, or three, depending on which category is most similar to the generated model. Its contribution is to create a predictive model for new patent documents to obtain meaningful patent citations based on patent document types. Classification can help decision-making by providing predictions of the most likely type or class of inventions based on new input data documents. the study is to obtain documents that can be used as a reference to measure and evaluate the taxonomy pattern applied in Indonesian patent documents; can save time and effort in tasks such as sorting patent similarity data, checking patent documents . Key word: Patent, Patent Classification, IPC (International Patent Classification)

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Ilmu Teknik Teknik Informatika
Subjects:	T Technology > T Technology (General) > T10.5-11.9 Communication of technical information
Divisions:	03-Faculty of Engineering > 21001-Engineering Science (S3)
Depositing User:	Slamet Widodo
Date Deposited:	27 May 2025 04:30
Last Modified:	27 May 2025 04:34
URI:	http://repository.unsri.ac.id/id/eprint/174255

Actions (login required)

View Item