Do Data Warehouse à Narrativa: Uma Arquitetura HTAP para Análise de Dados de Criminalidade
Resumo
Este artigo propõe a plataforma CrimeSmartScribe para análise de dados de criminalidade, com ingestão contínua e suporte a consultas em linguagem natural e dashboards interativos. A abordagem baseia-se em um modelo lógico multidimensional em ambiente híbrido transacional/analítico (HTAP) e emprega (i) visões virtuais, (ii) estratégias de geração aumentada de recuperação (RAG) e (iii) uma arquitetura multiagente para tradução texto-para-SQL e geração das respostas em tons jornalísticos com infográficos. Avaliada em dados criminais norte-americanos, a solução demonstrou robustez operacional, melhoria na tradução texto-para-SQL com o uso de RAG e alcançou altos índices de usabilidade entre usuários especialistas e não especialistas.
Palavras-chave:
HTAP, Sistemas Multiagentes, Jornalismo de Dados
Referências
Chen, J., Zhang, L., Xie, Y., Ding, W., Cao, L., Liu, Y., Ding, Y., Li, F., Wu, K., Xiu, H., et al. (2025). Vedb-HTAP: a highly integrated, efficient and adaptive HTAP system. Proceedings of the VLDB Endowment, 18(12):4896–4909.
Chien, Y.-C., Wang, K.-D., Wang, W.-Y., and Peng, W.-C. (2025). NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks. arXiv preprint arXiv:2509.00446.
Coelho, G. M., Nascimento, E. R., Izquierdo, Y. T., García, G. M., Feijó, L., Lemos, M., Garcia, R. L., de Oliveira, A. R., Pinheiro, J. P., and Casanova, M. A. (2024). Improving the accuracy of text-to-sql tools based on large language models for real-world relational databases. In International Conference on Database and Expert Systems Applications, pages 93–107. Springer.
Diakopoulos, N. (2019). Automating the news: How algorithms are rewriting the media. Harvard University Press.
Dong, Y., Jiang, X., Jin, Z., and Li, G. (2024). Self-collaboration code generation via ChatGPT. ACM Transactions on Software Engineering and Methodology, 33(7):1–38.
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., and Li, Q. (2024). A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining, pages 6491–6501.
Ferber, J. and Weiss, G. (1999). Multi-agent systems: an introduction to distributed artificial intelligence, volume 1. Addison-wesley Reading.
Fürst, J., Kosten, C., Nooralahzadeh, F., Zhang, Y., and Stockinger, K. (2024). Evaluating the data model robustness of text-to-sql systems based on real user queries. arXiv preprint arXiv:2402.08349.
García-Gil, D., Ramírez-Gallego, S., García, S., and Herrera, F. (2017). A comparison on scalability for batch big data processing on Apache Spark and Apache Flink. Big Data Analytics, 2(1):1.
Greenspan, R. L., Baggett, L., and B. Boutwell, B. (2024). Open science practices in criminology and criminal justice journals. Journal of Experimental Criminology, pages 1–21.
Hidalgo, J. J. P. and Centeno, J. A. S. (2023). Environmental scanning of cocaine trafficking in Brazil: Evidence from geospatial intelligence and natural language processing methods. Science & Justice, 63(6):689–723.
Jamil, H. M. and Rubaiat, S. Y. (2024). Online Digital Investigative Journalism Using SociaLens. In International Conference on Information Integration and Web Intelligence, pages 103–117. Springer.
Luo, Y., Li, G., Fan, J., Chai, C., and Tang, N. (2025). Natural language to sql: State of the art and open problems. Proceedings of the VLDB Endowment, 18(12):5466–5471.
Maltezos, V., Kyrychenko, R., and Knuutila, A. (2025). How can AI agents support journalists’ work? An experiment with designing an LLM-driven intelligent reporting system. arXiv preprint arXiv:2510.01193.
Miehling, E., Ramamurthy, K. N., Varshney, K. R., Riemer, M., Bouneffouf, D., Richards, J. T., Dhurandhar, A., Daly, E. M., Hind, M., Sattigeri, P., et al. (2025). Agentic AI needs a systems theory. arXiv preprint arXiv:2503.00237.
Mohan, R. K., Kanmani, R. R. S., Ganesan, K. A., and Ramasubramanian, N. (2024). Evaluating NoSQL Databases for OLAP Workloads: A Benchmarking Study of MongoDB, Redis, Kudu and ArangoDB. arXiv preprint arXiv:2405.17731.
Mtchedlidze, J. (2024). Technical Expertise in Newsrooms: Understanding Data Journalists’ Roles and Practices. Journalism and Media, 5(3):1316–1328.
Pan, J. J., Wang, J., and Li, G. (2024). Survey of vector database management systems. The VLDB Journal, 33(5):1591–1615.
Shi, L., Tang, Z., Zhang, N., Zhang, X., and Yang, Z. (2025). A survey on employing large language models for text-to-sql tasks. ACM Computing Surveys, 58(2):1–37.
Silva, R., Chagnoux, M., and Vassiliadis, P. (2022). Data Narrative Crafting via a Comprehensive and Well-Founded Process. In Advances in Databases and Information Systems, page 347. Springer.
Siqueira, P., Dias, R., Silva-Leite, J., Mann, P., Salvador, R., de Oliveira, D., and Bedo, M. (2025). Warehousing Data for Brand Health and Reputation with AI-Driven Scores in NewSQL Architectures: Opportunities and Challenges. International Conference on Enterprise Information Systems, pages 1–12.
Taft, R., Sharif, I., Matei, A., VanBenschoten, N., Lewis, J., Grieger, T., Niemi, K., Woods, A., Birzin, A., Poss, R., et al. (2020). Cockroachdb: The resilient geo-distributed sql database. In Proceedings of the 2020 ACM SIGMOD international conference on management of data, pages 1493–1509.
Zaharia, M. (2025). Bringing the Operational and Analytical Worlds Together with Lake-base. Proceedings of the VLDB Endowment, 18(12):5539–5539.
Chien, Y.-C., Wang, K.-D., Wang, W.-Y., and Peng, W.-C. (2025). NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks. arXiv preprint arXiv:2509.00446.
Coelho, G. M., Nascimento, E. R., Izquierdo, Y. T., García, G. M., Feijó, L., Lemos, M., Garcia, R. L., de Oliveira, A. R., Pinheiro, J. P., and Casanova, M. A. (2024). Improving the accuracy of text-to-sql tools based on large language models for real-world relational databases. In International Conference on Database and Expert Systems Applications, pages 93–107. Springer.
Diakopoulos, N. (2019). Automating the news: How algorithms are rewriting the media. Harvard University Press.
Dong, Y., Jiang, X., Jin, Z., and Li, G. (2024). Self-collaboration code generation via ChatGPT. ACM Transactions on Software Engineering and Methodology, 33(7):1–38.
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., and Li, Q. (2024). A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining, pages 6491–6501.
Ferber, J. and Weiss, G. (1999). Multi-agent systems: an introduction to distributed artificial intelligence, volume 1. Addison-wesley Reading.
Fürst, J., Kosten, C., Nooralahzadeh, F., Zhang, Y., and Stockinger, K. (2024). Evaluating the data model robustness of text-to-sql systems based on real user queries. arXiv preprint arXiv:2402.08349.
García-Gil, D., Ramírez-Gallego, S., García, S., and Herrera, F. (2017). A comparison on scalability for batch big data processing on Apache Spark and Apache Flink. Big Data Analytics, 2(1):1.
Greenspan, R. L., Baggett, L., and B. Boutwell, B. (2024). Open science practices in criminology and criminal justice journals. Journal of Experimental Criminology, pages 1–21.
Hidalgo, J. J. P. and Centeno, J. A. S. (2023). Environmental scanning of cocaine trafficking in Brazil: Evidence from geospatial intelligence and natural language processing methods. Science & Justice, 63(6):689–723.
Jamil, H. M. and Rubaiat, S. Y. (2024). Online Digital Investigative Journalism Using SociaLens. In International Conference on Information Integration and Web Intelligence, pages 103–117. Springer.
Luo, Y., Li, G., Fan, J., Chai, C., and Tang, N. (2025). Natural language to sql: State of the art and open problems. Proceedings of the VLDB Endowment, 18(12):5466–5471.
Maltezos, V., Kyrychenko, R., and Knuutila, A. (2025). How can AI agents support journalists’ work? An experiment with designing an LLM-driven intelligent reporting system. arXiv preprint arXiv:2510.01193.
Miehling, E., Ramamurthy, K. N., Varshney, K. R., Riemer, M., Bouneffouf, D., Richards, J. T., Dhurandhar, A., Daly, E. M., Hind, M., Sattigeri, P., et al. (2025). Agentic AI needs a systems theory. arXiv preprint arXiv:2503.00237.
Mohan, R. K., Kanmani, R. R. S., Ganesan, K. A., and Ramasubramanian, N. (2024). Evaluating NoSQL Databases for OLAP Workloads: A Benchmarking Study of MongoDB, Redis, Kudu and ArangoDB. arXiv preprint arXiv:2405.17731.
Mtchedlidze, J. (2024). Technical Expertise in Newsrooms: Understanding Data Journalists’ Roles and Practices. Journalism and Media, 5(3):1316–1328.
Pan, J. J., Wang, J., and Li, G. (2024). Survey of vector database management systems. The VLDB Journal, 33(5):1591–1615.
Shi, L., Tang, Z., Zhang, N., Zhang, X., and Yang, Z. (2025). A survey on employing large language models for text-to-sql tasks. ACM Computing Surveys, 58(2):1–37.
Silva, R., Chagnoux, M., and Vassiliadis, P. (2022). Data Narrative Crafting via a Comprehensive and Well-Founded Process. In Advances in Databases and Information Systems, page 347. Springer.
Siqueira, P., Dias, R., Silva-Leite, J., Mann, P., Salvador, R., de Oliveira, D., and Bedo, M. (2025). Warehousing Data for Brand Health and Reputation with AI-Driven Scores in NewSQL Architectures: Opportunities and Challenges. International Conference on Enterprise Information Systems, pages 1–12.
Taft, R., Sharif, I., Matei, A., VanBenschoten, N., Lewis, J., Grieger, T., Niemi, K., Woods, A., Birzin, A., Poss, R., et al. (2020). Cockroachdb: The resilient geo-distributed sql database. In Proceedings of the 2020 ACM SIGMOD international conference on management of data, pages 1493–1509.
Zaharia, M. (2025). Bringing the Operational and Analytical Worlds Together with Lake-base. Proceedings of the VLDB Endowment, 18(12):5539–5539.
Publicado
08/09/2026
Como Citar
SERRA, Ryan; RIBEIRO, Daniel; TAFILI, Arben H. S.; COSTA-JR., Paulo S.; SILVA-LEITE, João V.; MONTEIRO, Rodrigo S.; DE OLIVEIRA, Daniel; BEDO, Marcos.
Do Data Warehouse à Narrativa: Uma Arquitetura HTAP para Análise de Dados de Criminalidade. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 15-28.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2026.249116.
