Uma proposta de Modelo Arquitetural Neuro-Simbólico para suporte à avaliação de Políticas de CT&I baseada em evidências
Resumo
A gestão de políticas públicas em Ciência, Tecnologia e Inovação (CT&I) enfrenta o desafio da fragmentação de dados. Este trabalho propõe uma arquitetura neuro-simbólica para o povoamento automatizado de Grafos de Conhecimento (KGs) utilizando Modelos de Linguagem de Larga Escala (LLMs). A arquitetura é estruturada em quatro componentes funcionais: ingestão híbrida de métricas de CT&I, processamento via pipelines de extração de entidades e relações, persistência semântica em RDF e aplicação para suporte à decisão. Como resultado, a solução transforma dados brutos em inteligência acionável, permitindo a identificação de lacunas de inovação e a otimização da alocação de recursos públicos baseada em evidências sólidas.Referências
Abu-Salih, B., Alotaibi, S., Alanazi, A. L., Abu Khurma, R., Al-Shboul, B., Khouri, A., and Aljaafari, M. (2025). Using large language models for semantic interoperability: A systematic literature review. ICT Express, 11(4):819–837. DOI: 10.1016/j.icte.2025.06.011.
Arya, V., Saraf, A., Chichkanov, N., Papa, A., and Romano, M. (2026). AI-enhanced competency transfer hubs: a conceptual framework for university-industry engagement and knowledge sharing. The Journal of Technology Transfer, 51(2):682–712. DOI: 10.1007/s10961-025-10233-7.
Bellomarini, L., Fayzrakhmanov, R. R., Gottlob, G., Kravchenko, A., Laurenza, E., Nenov, Y., Reissfelder, S., Sallinger, E., Sherkhonov, E., Vahdati, S., and Wu, L. (2022). Data science with Vadalog: Knowledge Graphs with machine learning and reasoning in practice. Future Generation Computer Systems, 129:407–422. DOI: 10.1016/j.future.2021.10.021.
Benjira, W., Atigui, F., Bucher, B., Grim-Yefsah, M., and Travers, N. (2025). Automated mapping between SDG indicators and open data: An LLM-augmented knowledge graph approach. Data & Knowledge Engineering, 156:102405. DOI: 10.1016/j.datak.2024.102405.
Bergek, A., Hellsmark, H., and Karltorp, K. (2023). Directionality challenges for transformative innovation policy: lessons from implementing climate goals in the process industry. Industry and Innovation, 30(8):1110–1139. DOI: 10.1080/13662716.2022.2163882.
Colombo, A., Bernasconi, A., and Ceri, S. (2025). An LLM-assisted ETL pipeline to build a high-quality knowledge graph of the Italian legislation. Information Processing & Management, 62(4):104082. DOI: 10.1016/j.ipm.2025.104082.
Dessı̀, D., Osborne, F., Reforgiato Recupero, D., Buscaldi, D., and Motta, E. (2021). Generating knowledge graphs by employing Natural Language Processing and Machine Learning techniques within the scholarly domain. Future Generation Computer Systems, 116:253–264. DOI: 10.1016/j.future.2020.10.026.
Doumanas, D., Ntalouka, E., Vassilakis, C., Wallace, M., and Kotis, K. (2025). Stitching History into Semantics: LLM-Supported Knowledge Graph Engineering for 19th-Century Greek Bookbinding. Machine Learning and Knowledge Extraction, 7(3):59. DOI: 10.3390/make7030059.
Dreger, M., Malek, K., and Eikerling, M. (2025). Large language models for knowledge graph extraction from tables in materials science. Digital Discovery, 4(5):1221–1231. DOI: 10.1039/D4DD00362D.
Gokhberg, L., Fursov, K., Miles, I., and Perani, G. (2013). Chapter 15: Developing and using indicators of emerging and enabling technologies. In Handbook of Innovation Indicators and Measurement. Edward Elgar Publishing. Section: Handbook of Innovation Indicators and Measurement. DOI: 10.4337/9780857933652.00027.
Hoseini, S., Theissen-Lipp, J., and Quix, C. (2024). A survey on semantic data management as intersection of ontology-based data access, semantic modeling and data lakes. Journal of Web Semantics, 81:100819. DOI: 10.1016/j.websem.2024.100819.
Kalaycı, T. E., Bricelj, B., Lah, M., Pichler, F., Scharrer, M. K., and Rubeša-Zrim, J. (2021). A Knowledge Graph-Based Data Integration Framework Applied to Battery Data Management. Sustainability, 13(3):1583. DOI: 10.3390/su13031583.
Malec, S. A., Taneja, S. B., Albert, S. M., Elizabeth Shaaban, C., Karim, H. T., Levine, A. S., Munro, P., Callahan, T. J., and Boyce, R. D. (2023). Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: A use case studying depression as a risk factor for Alzheimer’s disease. Journal of Biomedical Informatics, 142:104368. DOI: 10.1016/j.jbi.2023.104368.
Meroño-Peñuela, A., Simperl, E., Kurteva, A., and Reklos, I. (2025). KG.GOV: Knowledge graphs as the backbone of data governance in AI. Journal of Web Semantics, 85:100847. DOI: 10.1016/j.websem.2024.100847.
Ouzounis, S., Kanterakis, A., Panagiotopoulos, V., Cavouras, D., Zoumpoulakis, P., Matsoukas, M.-T., Katsila, T., and Kalatzis, I. (2023). Data-Driven Drug Repurposing in Diabetes Mellitus through an Enhanced Knowledge Graph. Engineering Proceedings, 50(1):9. DOI: 10.3390/engproc2023050009.
Reese, J. T., Unni, D., Callahan, T. J., Cappelletti, L., Ravanmehr, V., Carbon, S., Shefchek, K. A., Good, B. M., Balhoff, J. P., Fontana, T., Blau, H., Matentzoglu, N., Harris, N. L., Munoz-Torres, M. C., Haendel, M. A., Robinson, P. N., Joachimiak, M. P., and Mungall, C. J. (2021). KG-COVID-19: A Framework to Produce Customized Knowledge Graphs for COVID-19 Response. Patterns, 2(1). DOI: 10.1016/j.patter.2020.100155.
Shimizu, C. and Hitzler, P. (2025). Accelerating knowledge graph and ontology engineering with large language models. Journal of Web Semantics, 85:100862. DOI: 10.1016/j.websem.2025.100862.
Vidal, M.-E., Chudasama, Y., Huang, H., Purohit, D., and Torrente, M. (2025). Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine. Journal of Web Semantics, 84:100856. DOI: 10.1016/j.websem.2024.100856.
Wu, L.-x., Jiang, Y., Luo, T.-y., Hou, J.-x., Deng, Y., Han, L.-x., Jiang, T.-f., and Bao, J. (2025). Interpretable AI-assisted diagnosis of papillary thyroid cancer cytopathology using graph neural networks and knowledge graphs. Scientific Reports, 15(1):32165. DOI: 10.1038/s41598-025-18235-z.
Arya, V., Saraf, A., Chichkanov, N., Papa, A., and Romano, M. (2026). AI-enhanced competency transfer hubs: a conceptual framework for university-industry engagement and knowledge sharing. The Journal of Technology Transfer, 51(2):682–712. DOI: 10.1007/s10961-025-10233-7.
Bellomarini, L., Fayzrakhmanov, R. R., Gottlob, G., Kravchenko, A., Laurenza, E., Nenov, Y., Reissfelder, S., Sallinger, E., Sherkhonov, E., Vahdati, S., and Wu, L. (2022). Data science with Vadalog: Knowledge Graphs with machine learning and reasoning in practice. Future Generation Computer Systems, 129:407–422. DOI: 10.1016/j.future.2021.10.021.
Benjira, W., Atigui, F., Bucher, B., Grim-Yefsah, M., and Travers, N. (2025). Automated mapping between SDG indicators and open data: An LLM-augmented knowledge graph approach. Data & Knowledge Engineering, 156:102405. DOI: 10.1016/j.datak.2024.102405.
Bergek, A., Hellsmark, H., and Karltorp, K. (2023). Directionality challenges for transformative innovation policy: lessons from implementing climate goals in the process industry. Industry and Innovation, 30(8):1110–1139. DOI: 10.1080/13662716.2022.2163882.
Colombo, A., Bernasconi, A., and Ceri, S. (2025). An LLM-assisted ETL pipeline to build a high-quality knowledge graph of the Italian legislation. Information Processing & Management, 62(4):104082. DOI: 10.1016/j.ipm.2025.104082.
Dessı̀, D., Osborne, F., Reforgiato Recupero, D., Buscaldi, D., and Motta, E. (2021). Generating knowledge graphs by employing Natural Language Processing and Machine Learning techniques within the scholarly domain. Future Generation Computer Systems, 116:253–264. DOI: 10.1016/j.future.2020.10.026.
Doumanas, D., Ntalouka, E., Vassilakis, C., Wallace, M., and Kotis, K. (2025). Stitching History into Semantics: LLM-Supported Knowledge Graph Engineering for 19th-Century Greek Bookbinding. Machine Learning and Knowledge Extraction, 7(3):59. DOI: 10.3390/make7030059.
Dreger, M., Malek, K., and Eikerling, M. (2025). Large language models for knowledge graph extraction from tables in materials science. Digital Discovery, 4(5):1221–1231. DOI: 10.1039/D4DD00362D.
Gokhberg, L., Fursov, K., Miles, I., and Perani, G. (2013). Chapter 15: Developing and using indicators of emerging and enabling technologies. In Handbook of Innovation Indicators and Measurement. Edward Elgar Publishing. Section: Handbook of Innovation Indicators and Measurement. DOI: 10.4337/9780857933652.00027.
Hoseini, S., Theissen-Lipp, J., and Quix, C. (2024). A survey on semantic data management as intersection of ontology-based data access, semantic modeling and data lakes. Journal of Web Semantics, 81:100819. DOI: 10.1016/j.websem.2024.100819.
Kalaycı, T. E., Bricelj, B., Lah, M., Pichler, F., Scharrer, M. K., and Rubeša-Zrim, J. (2021). A Knowledge Graph-Based Data Integration Framework Applied to Battery Data Management. Sustainability, 13(3):1583. DOI: 10.3390/su13031583.
Malec, S. A., Taneja, S. B., Albert, S. M., Elizabeth Shaaban, C., Karim, H. T., Levine, A. S., Munro, P., Callahan, T. J., and Boyce, R. D. (2023). Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: A use case studying depression as a risk factor for Alzheimer’s disease. Journal of Biomedical Informatics, 142:104368. DOI: 10.1016/j.jbi.2023.104368.
Meroño-Peñuela, A., Simperl, E., Kurteva, A., and Reklos, I. (2025). KG.GOV: Knowledge graphs as the backbone of data governance in AI. Journal of Web Semantics, 85:100847. DOI: 10.1016/j.websem.2024.100847.
Ouzounis, S., Kanterakis, A., Panagiotopoulos, V., Cavouras, D., Zoumpoulakis, P., Matsoukas, M.-T., Katsila, T., and Kalatzis, I. (2023). Data-Driven Drug Repurposing in Diabetes Mellitus through an Enhanced Knowledge Graph. Engineering Proceedings, 50(1):9. DOI: 10.3390/engproc2023050009.
Reese, J. T., Unni, D., Callahan, T. J., Cappelletti, L., Ravanmehr, V., Carbon, S., Shefchek, K. A., Good, B. M., Balhoff, J. P., Fontana, T., Blau, H., Matentzoglu, N., Harris, N. L., Munoz-Torres, M. C., Haendel, M. A., Robinson, P. N., Joachimiak, M. P., and Mungall, C. J. (2021). KG-COVID-19: A Framework to Produce Customized Knowledge Graphs for COVID-19 Response. Patterns, 2(1). DOI: 10.1016/j.patter.2020.100155.
Shimizu, C. and Hitzler, P. (2025). Accelerating knowledge graph and ontology engineering with large language models. Journal of Web Semantics, 85:100862. DOI: 10.1016/j.websem.2025.100862.
Vidal, M.-E., Chudasama, Y., Huang, H., Purohit, D., and Torrente, M. (2025). Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine. Journal of Web Semantics, 84:100856. DOI: 10.1016/j.websem.2024.100856.
Wu, L.-x., Jiang, Y., Luo, T.-y., Hou, J.-x., Deng, Y., Han, L.-x., Jiang, T.-f., and Bao, J. (2025). Interpretable AI-assisted diagnosis of papillary thyroid cancer cytopathology using graph neural networks and knowledge graphs. Scientific Reports, 15(1):32165. DOI: 10.1038/s41598-025-18235-z.
Publicado
19/07/2026
Como Citar
BARBOSA, Ricardo Luiz de Carvalho; SOUZA, Ricardo André Cavalcante de.
Uma proposta de Modelo Arquitetural Neuro-Simbólico para suporte à avaliação de Políticas de CT&I baseada em evidências. In: LATIN AMERICAN SYMPOSIUM ON DIGITAL GOVERNMENT (LASDIGOV), 14. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 301-312.
ISSN 2763-8723.
DOI: https://doi.org/10.5753/lasdigov.2026.23304.
