Prova de Conceito de um Classificador de OPMEs em Notas Fiscais

• Wesckley Gomes UFRN / IFRN / UFS
• Methanias Colaço Júnior UFRN / IFRN / UFS
• Raphael Fontes UFRN / IFRN
• Rodrigo Silva UFRN
• Bruno Nunes Ministério da Saúde
• Caldeira Silva UFRN / IFRN
• Jailton Paiva UFRN / IFRN
• Ricardo Valetim UFRN / IFRN

DOI: https://doi.org/10.5753/sbcas_estendido.2023.231487

Abstract

Context: Despite the advancement of technology, many services and information systems, especially in the public sector, still use unstructured descriptions in natural language of products, services or events, making their classification and analysis difficult. For efficient audits, it is necessary automatically classify and total invoices issued for the purchase of products. Objective: Preliminarily evaluate a tool, based on artificial intelligence, to classify OPME invoices. Method: A proof-of-concept study was carried out in the OPMinEr project. Results: The results show that it is possible to identify and classify OPMEs in invoices. Conclusion: The use of artificial intelligence techniques helped to mitigate the problem of classifying and analyzing invoices, thus helping in auditing, investigation and anti-corruption processes.

References

Batista, R. d., Bagatini, D. D., & Frozza, R. (2017). Classificação Automática de Códigos NCM utilizando o Algoritmo de Naïve Bayes. Revista Brasileira de Sist. de Inf., 13, 4-29.

Carmo de Souza Cruz, R. a. (2022). Análise do impacto do Banco de Preços em Saúde (BPS) para redução das assimetrias de informação dos preços de compras de Órteses, Prótese e Materiais Especiais (OPME). JMPHC Journal of Manag. & Primary Health Care, 14.

Correa, M. A., & Leal, A. (2018). Identification of Overpricing in the Purchase of Medication by the Federal Government of Brazil, Using Text Mining and Clustering Based on Ontology. ICCBDC'18: Proceedings of the 2018 2nd International Conference on Cloud and Big Data Computing, 66-70. doi:10.1145/3264560.3264569

Cruz, R., Colaço Júnior, M., & Gois, V. 2022). Quão experimentais e estratégicas são as aplicações de Business Intelligence (BI) e Data Mining? ; HOW EXPERIMENTAL AND STRATEGIC ARE BUSINESS INTELLIGENCE (BI) AND DATA MINING APPLICATIONS? Revista Ibero-Americana de Estratégia, 21, e17689.

Gomes, W., & Colaço Júnior, M. (2022). Applications of Artificial Intelligence for Auditing and Classification of Incongruent Descriptions in Public Procurement. Proceedings of the Brazilian Symposium on Information Systems (pp. 1-8).

Ribeiro, L., Brandão, W., Marques, Í., Andrade, P., Júnior, R., Oliveira, F., & Kelles, R. (2018). Reconhecimento de entidades nomeadas em itens de produto da nota fiscal eletrônica., 36, pp. 116-126.

Santos, B., Colaço Júnior, M., Meneses Santos, R., & Nascimento, A. (2015). Análise Comparativa de Algoritmos de Mineração de Texto Aplicados a Históricos de Contas Públicas. Proceedings of the Brazilian Symposium on Information Systems.

Spichakova, M., & Haav, H.-m. (2020). Using Machine Learning for Automated Assessment of Misclassification of Goods for Fraud Detection., (pp. 144-158). doi:10.1007/978-3-030-57672-1_12

TCU. 2016). Auditoria em òrtese, Prótese e Materiais Especiais (OPME). Fonte: Portal TCU: [link].