Innovative data extraction in patent reviews with SciSpace

IF 1.9 Q2 INFORMATION SCIENCE & LIBRARY SCIENCE

World Patent Information Pub Date : 2025-07-11 DOI:10.1016/j.wpi.2025.102377

Paula dos Passos Menezes , Alcimary Bispo Santos , Maria Eduarda da Conceição Andrade , José Adão Carvalho Nascimento Júnior , Marcelo Cavalcante Duarte , Shanmugan Saravanan , Mairim Russo Serafini

{"title":"Innovative data extraction in patent reviews with SciSpace","authors":"Paula dos Passos Menezes , Alcimary Bispo Santos , Maria Eduarda da Conceição Andrade , José Adão Carvalho Nascimento Júnior , Marcelo Cavalcante Duarte , Shanmugan Saravanan , Mairim Russo Serafini","doi":"10.1016/j.wpi.2025.102377","DOIUrl":null,"url":null,"abstract":"<div><div>Patent review is a time-consuming process because it involves the complexity of the documents with technical language and unpatterned files. Automating steps like data extraction can make technological prospects faster and more efficient. Thus, this study aimed to compare the use of an Artificial Intelligence (AI) tool to automate the data extraction of patents. A traditional patent review was conducted in Espacenet and WIPO databases, using the test subject: AI tools for skin cancer detection. Two independent reviewers performed the patent screening in Excel traditionally, and the data extraction step was manually made both and using SciSpace. SciSpace was 13.2 times faster than the traditional way and correctly extracted 69.7 % of information. Although it is a promising tool to accelerate the patent review process, it is crucial to author review the final version to ensure its accuracy and the representation of its ideas.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"82 ","pages":"Article 102377"},"PeriodicalIF":1.9000,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"World Patent Information","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0172219025000444","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Patent review is a time-consuming process because it involves the complexity of the documents with technical language and unpatterned files. Automating steps like data extraction can make technological prospects faster and more efficient. Thus, this study aimed to compare the use of an Artificial Intelligence (AI) tool to automate the data extraction of patents. A traditional patent review was conducted in Espacenet and WIPO databases, using the test subject: AI tools for skin cancer detection. Two independent reviewers performed the patent screening in Excel traditionally, and the data extraction step was manually made both and using SciSpace. SciSpace was 13.2 times faster than the traditional way and correctly extracted 69.7 % of information. Although it is a promising tool to accelerate the patent review process, it is crucial to author review the final version to ensure its accuracy and the representation of its ideas.

查看原文本刊更多论文

创新的数据提取在专利审查与SciSpace

专利审查是一个耗时的过程，因为它涉及到具有技术语言和无图案文件的文件的复杂性。像数据提取这样的自动化步骤可以使技术前景更快、更有效。因此，本研究旨在比较人工智能（AI）工具在自动化专利数据提取中的使用情况。在Espacenet和WIPO数据库中进行了传统的专利审查，测试主题为：用于皮肤癌检测的人工智能工具。传统上由两名独立审查员在Excel中进行专利筛选，数据提取步骤由人工完成，并使用SciSpace进行。该方法比传统方法快13.2倍，正确率达69.7%。虽然它是加速专利审查过程的一个有前途的工具，但作者审查最终版本以确保其准确性和其思想的代表性至关重要。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

World Patent Information INFORMATION SCIENCE & LIBRARY SCIENCE-

CiteScore

3.50

自引率

18.50%

发文量

期刊介绍： The aim of World Patent Information is to provide a worldwide forum for the exchange of information between people working professionally in the field of Industrial Property information and documentation and to promote the widest possible use of the associated literature. Regular features include: papers concerned with all aspects of Industrial Property information and documentation; new regulations pertinent to Industrial Property information and documentation; short reports on relevant meetings and conferences; bibliographies, together with book and literature reviews.