MiraBR – A System for Patent Analysis
Resumo
Context: Innovation is essential for economic and technological development, with patents serving as a key metric to monitor and stimulate this innovation. However, patent information is often fragmented and distributed across isolated systems, hindering strategic and global analyses. Problem: The lack of integration between patent databases limits the ability to conduct comparative and evolutionary analyses, thereby restricting efforts to identify trends, prospect opportunities, and monitor international competitiveness. Solution: The MiraBR system was developed as an open-source web application that collects, integrates, and analyzes patent data from multiple national and international sources. Using a web crawler, data is extracted from databases such as INPI, Derwent, and Espacenet, processed, and integrated into a centralized database. The system supports multi-language search queries and enables analyses based on classifications, countries, inventors, and patent holders. It also provides intuitive visualizations that facilitate strategic and comparative analysis. IS Theory: This work is conceived under the Socio-technical theory, as the system integrates human and technical elements. Method: The research involved a proof of concept to validate the system’s core functionalities and a quasi-experiment to assess its usability and effectiveness in real-world scenarios. The quasi-experiment included specialists from the intellectual property field, who evaluated the system’s performance and relevance through practical application and structured questionnaires. The analysis approach was descriptive, aiming to present the system’s capabilities and its alignment with user needs, with a focus on quantitative metrics (e.g., precision and recall) and qualitative feedback (e.g., usability assessments). This mixed-method approach ensured a comprehensive evaluation of the system, addressing both technical performance and user satisfaction. Results: The system was evaluated by INPI experts and received high approval for its ease of use, rich visualizations, and quality of the analyses. Precision and recall metrics indicated satisfactory performance in information retrieval. Contributions: MiraBR contributes to innovation management by enabling integrated strategic analyses of patents, enhancing technological support for science and innovation in Brazil. It also paves the way for future research in data mining and visualization applied to the domain.
Referências
[n. d.]. Espacenet. [link]. [Accessed 18-11-2024].
[n. d.]. Foundations for rebuilding Brazil’s scientific capacity — revistapesquisa. fapesp.br. [link]. [Accessed 18-11-2024].
[n. d.]. INPI - Instituto Nacional da Propriedade Industrial. [link]. [Accessed 18-11-2024].
[n. d.]. Patentes. [link]. [Accessed 18-11-2024].
[n. d.]. Science, Technology, and Innovation in Brazil — unesco.org. [link]. [Accessed 18-11-2024].
Ricardo Baeza-Yates, Berthier Ribeiro-Neto, et al. 1999. Modern information retrieval. Vol. 463. ACM press New York.
Clodis Boscarioli, Renata Mendes de Araujo, Rita Suzana Maciel, Valdemar Vicente Graciano Neto, Flavio Oquendo, Elisa Yumi Nakagawa, Flavia Cristina Berrnardini, José Viterbo, Dalessandro Vianna, Carlos Bazilio Martins, et al. 2017. I GranDSI-BR: Grand Research Challenges in Information Systems in Brazil 2016-2026. (2017).
BRASIL. 1996. Lei 9279, de 14 de maio de 1996. Publicada no Diário Oficial da União em 15 de maio de 1996. [Accessed 18-11-2024].
BRASIL. 1998. Lei 9609, de 19 de fevereiro de 1998. Publicada no Diário Oficial da União em 20 de fevereiro de 1998. [Accessed 18-11-2024].
Paula Cotrim de Abrantes, Daniel Barros Junior, Elisângela Aparecida da Silva, Genízia Islabão Islabão, and Douglas Alves Santos. 2022. Estudo comparativo de bases gratuitas de patentes: patentscope (wipo), espacenet (epo), buscaweb (inpi/br). Revista Tecnologia e Sociedade 18, 54 (2022), 125–142.
Fred E Emery and Eric L Trist. 1960. Socio-technical systems. Management science, models and techniques 2 (1960), 83–97.
Patrick Kochan, Bartholomeo Barcelos, and Alexandre Gonçalves. 2024. Identifying Technological Trends: A Patent Analysis Method for Technology Forecasting. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados (Florianópolis/SC). SBC, Porto Alegre, RS, Brasil, 327–340. DOI: 10.5753/sbbd.2024.240268
Farshad Madani. 2015. ‘Technology Mining’bibliometrics analysis: applying network analysis and cluster analysis. Scientometrics 105, 1 (2015), 323–335.
Suzana Pinheiro Machado Mueller and Valmira Perucchi. 2014. Universidades e a produção de patentes: tópicos de interesse para o estudioso da informação tecnológica. Perspectivas em Ciência da Informação 19 (2014), 15–36.
Edilson Araújo Pires, Nubia Moura Ribeiro, and Cristina M Quintella. 2020. Sistemas de busca de patentes: análise comparativa entre espacenet, patentscope, google patents, lens, derwent innovation index e orbit intelligence. Cadernos de prospecção 13, 1 (2020), 13–13.
Lucas Resende, José Pérez-Alcázar, and Esteban Tuesta. 2021. Desenvolvimento de uma Ontologia de Patentes e criação de uma base de dados ligados para patentes brasileiras.
Serhad Sarica, Jianxi Luo, and Kristin L Wood. 2020. TechNet: Technology semantic network based on patent data. Expert Systems with Applications 142 (2020), 112995.
Sandro Luis Freire de Castro Silva, Maria Augusta Silveira Netto Nunes, Marcelo Fornazin, and Rodrigo Pereira dos Santos. 2021. The profusion of information systems to combat the covid-19 pandemic: A systematic mapping of the state of the art and brazilian challenges of technological production. In Proceedings of the XVII Brazilian Symposium on Information Systems. 1–8.
Amy Trappey, Charles V Trappey, and Alex Hsieh. 2021. An intelligent patent recommender adopting machine learning approach for natural language processing: A case study for smart machinery technology mining. Technological Forecasting and Social Change 164 (2021), 120511.
WIPO. 2022. International Patent Classification (IPC) — wipo.int. [link]. [Accessed 18-11-2024].
WIPO WIPO. 2023. Intellectual Property Handbook: Policy, Law and Use, WIPO Publication no. 489 (E)(2008).
Yen-Chun JimWu and Hsing-Piao Liu. 2006. Technological innovation assessment of business-to-business electronic marketplaces. Journal of the American Society for Information Science and Technology 57, 8 (2006), 1093–1104.
Xiaobing Xue and W Bruce Croft. 2009. Automatic query generation for patent search. In Proceedings of the 18th ACM conference on Information and knowledge management. 2037–2040.
