Design of a Cognitive Decision Support System Using Knowledge Graphs and Deep Reinforcement Learning for Real-Time Emergency Response

Wei Yang; Wenjun Wang

doi:10.31081/dmame8220251605

Authors

Wei Yang Doctoral Engineering Candidate, College of Intelligent Computing, Tianjin University, Tianjin 300072
Wenjun Wang Professor, College of Intelligent Computing, Tianjin University, Tianjin 300072

DOI:

https://doi.org/10.31081/dmame8220251605

Keywords:

Cognitive Decision Support System, Knowledge Graphs, Deep Q-Network, Emergency Response, Reinforcement Learning

Abstract

Emergency response scenarios are inherently complex and rapidly evolving, necessitating immediate and well-informed decision-making. Traditional decision support systems, however, often struggle to effectively integrate heterogeneous data sources and adapt to continuously changing conditions. To address these challenges and enhance both the speed and quality of decision-making in emergency contexts, this study proposes a Cognitive Decision Support System for Emergency Response (CDSS-ER), which combines Knowledge Graphs (KGs) with Deep Reinforcement Learning (DRL), specifically Deep Q-Networks (DQN). The system constructs a dynamic KG by aggregating and semantically aligning data from multiple emergency-related sources, thereby capturing contextual and relational information in real time. These structured knowledge representations are then vectorised to depict the current state of the emergency environment. Leveraging these representations, the DQN component determines optimal response policies through iterative trial-and-error interactions, continuously refining its strategies based on real-time feedback. Experimental results demonstrate that CDSS-ER substantially outperforms conventional rule-based systems with respect to both the efficiency of resource allocation and the accuracy of decisions. The framework provides a scalable and adaptive solution for emergency management and holds promise for application in other domains requiring real-time cognitive decision support.

Downloads

Download data is not yet available.

References

[1] Abbas, A. N., Amazu, C. W., Mietkiewicz, J., Briwa, H., Perez, A. A., Baldissone, G., & Leva, M. C. (2024). Analyzing operator states and the impact of ai-enhanced decision support in control rooms: a human-in-the-loop specialized reinforcement learning framework for intervention strategies. International Journal of Human–Computer Interaction, 1-35. https://doi.org/10.1080/10447318.2024.2391605

[2] Aboualola, M., Abualsaud, K., Khattab, T., Zorba, N., & Hassanein, H. S. (2023). Edge technologies for disaster management: A survey of social media and artificial intelligence integration. IEEE Access, 11, 73782-73802. https://doi.org/10.1109/ACCESS.2023.3293035

[3] Abu-Rasheed, H., Nadeem, M., Dornhöfer, M., Zenkert, J., Weber, C., & Fathi, M. (2024). Texkg in health domain: The application of knowledge graph based framework for explainable recommendations in the contexts of elderly care, mental health, and emergency responses. In Integrated Systems: Data Driven Engineering (pp. 265-285). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-53652-6_16

[4] Arora, S. (2025). Transforming AI Decision Support System with Knowledge Graphs & CAG. International Journal on Engineering Artificial Intelligence Management, Decision Support, and Policies, 2(2), 15-23. https://doi.org/10.63503/j.ijaimd.2025.110

[5] Bajwa, A. (2025). AI-based emergency response systems: A systematic literature review on smart infrastructure safety. http://dx.doi.org/10.2139/ssrn.5171521

[6] Cepero, M. T., Montané-Jiménez, L. G., Toledo-Toledo, G., Benítez-Guerrero, E., & Mezura-Godoy, C. (2021). Heuristics for awareness support in groupware systems. Dyna New Technologies, 8(1). https://doi.org/10.6036/NT9980

[7] Chen, M., Tao, Z., Tang, W., Qin, T., Yang, R., & Zhu, C. (2024). Enhancing emergency decision-making with knowledge graphs and large language models. International Journal of Disaster Risk Reduction, 113, 104804. https://doi.org/10.1016/j.ijdrr.2024.104804

[8] Chen, S., Luo, G., & Chen, L. (2024). Intelligent Urban Emergency Response: Integrating Large Language Models, Multi-Objective Optimization, and Reinforcement Learning. 2024 IEEE Smart World Congress (SWC), 1469-1476. https://doi.org/ 10.1109/SWC62898.2024.00226

[9] Fan, J., Chang, X., Mišić, J., Mišić, V. B., & Kang, H. (2022). DHL: Deep reinforcement learning-based approach for emergency supply distribution in humanitarian logistics. Peer-to-Peer Networking and Applications, 15(5), 2376-2389. https://doi.org/10.1007/s12083-022-01353-0

[10] Gerolimos, N., Alevizos, V., Edralin, S., Xu, C., Priniotakis, G., Papakostas, G. A., & Yue, Z. (2025). Autonomous Decision-Making Enhancing Natural Disaster Management through Open World Machine Learning: A Systematic Review. Human-Centric Intelligent Systems, 1-16. https://doi.org/10.1007/s44230-025-00098-2

[11] He, F., Bai, W., & Wang, Z. (2025). Investigating the synergistic effects of temporal knowledge graphs and digital twin technologies to enhance situational awareness decision-making in smart cities. Journal of Computational Methods in Sciences and Engineering, 25(2), 1793-1810. https://doi.org/10.1177/14727978241305755

[12] He, L., Li, J., Zhao, M., & Yuan, R. (2022). Research on Emergency Logistics Decision Platform Based on Knowledge Graph. In International Conference on Logistics, Informatics and Service Sciences (pp. 199-210). Springer Nature Singapore. https://doi.org/10.1007/978-981-99-2625-1_15

[13] Kyrkou, C., Kolios, P., Theocharides, T., & Polycarpou, M. (2022). Machine learning for emergency management: A survey and future outlook. Proceedings of the IEEE, 111(1), 19-41. https://doi.org/10.1109/JPROC.2022.3223186

[14] Li, D., Zhang, Z., Alizadeh, B., Zhang, Z., Duffield, N., Meyer, M. A., & Behzadan, A. H. (2024). A reinforcement learning-based routing algorithm for large street networks. International Journal of Geographical Information Science, 38(2), 183-215. https://doi.org/10.1080/13658816.2023.2279975

[15] Li, M., Yuan, C., Li, K., Gao, M., Zhang, Y., & Lv, H. (2024). Knowledge Management Model for Urban Flood Emergency Response Based on Multimodal Knowledge Graphs. Water, 16(12), 1676. https://doi.org/10.3390/w16121676

[16] Li, Q., Zhang, M., Shen, Y., Wang, R., Hu, M., Li, Y., & Hao, H. (2023). A hierarchical deep reinforcement learning model with expert prior knowledge for intelligent penetration testing. Computers & Security, 132, 103358. https://doi.org/10.1016/j.cose.2023.103358

[17] Li, W., Wang, S., Chen, X., Tian, Y., Gu, Z., Lopez-Carr, A., & Zhu, R. (2023). Geographvis: a knowledge graph and geovisualization empowered cyberinfrastructure to support disaster response and humanitarian aid. ISPRS International Journal of Geo-Information, 12(3), 112. https://doi.org/10.3390/ijgi12030112

[18] Li, X., Chen, C. H., Zheng, P., Wang, Z., Jiang, Z., & Jiang, Z. (2020). A knowledge graph-aided concept–knowledge approach for evolutionary smart product–service system development. Journal of Mechanical Design, 142(10), 101403. https://doi.org/10.1115/1.4046807

[19] Li, X., Zhao, T., Wen, J., & Cai, X. (2024). Many-objective emergency aided decision making based on knowledge graph. Applied Intelligence, 54(17), 7733-7749. https://doi.org/10.1007/s10489-024-05557-0

[20] Linardos, V., Drakaki, M., Tzionas, P., & Karnavas, Y. L. (2022). Machine learning in disaster management: recent developments in methods and applications. Machine Learning and Knowledge Extraction, 4(2). https://doi.org/10.3390/make4020020

[21] Liu, M., Li, X., Li, J., Liu, Y., Zhou, B., & Bao, J. (2022). A knowledge graph-based data representation approach for IIoT-enabled cognitive manufacturing. Advanced Engineering Informatics, 51, 101515. https://doi.org/10.1016/j.aei.2021.101515

[22] Nussbaumer, A., Pope, A., & Neville, K. (2023). A framework for applying ethics-by-design to decision support systems for emergency management. Information Systems Journal, 33(1), 34-55. https://doi.org/10.1111/isj.12350

[23] Olan, F., Spanaki, K., Ahmed, W., & Zhao, G. (2025). Enabling explainable artificial intelligence capabilities in supply chain decision support making. Production Planning & Control, 36(6), 808-819. https://doi.org/10.1080/09537287.2024.2313514

[24] Peralta-Abadía, J. J., Cuesta-Zabaljauregui, M., & Larrinaga-Barrenechea, F. (2024). Tool condition monitoring in machining using robust residual neural networks. Dyna, 99(5). https://doi.org/10.52152/D11111

[25] Piadeh, F., Behzadian, K., Chen, A. S., Campos, L. C., Rizzuto, J. P., & Kapelan, Z. (2023). Event-based decision support algorithm for real-time flood forecasting in urban drainage systems using machine learning modelling. Environmental Modelling & Software, 167, 105772. https://doi.org/10.1016/j.envsoft.2023.105772

[26] Sasikumar, A., Ravi, L., Devarajan, M., Kotb, H., & Subramaniyaswamy, V. (2024). Cognitive Computing System-Based Dynamic Decision Control for Smart City Using Reinforcement Learning Model. In Cognitive Analytics and Reinforcement Learning: Theories, Techniques and Applications (pp. 29-50). https://doi.org/10.1002/9781394214068.ch2

[27] Shan, S., & Li, Y. (2024). Research on the application framework of generative AI in emergency response decision support systems for emergencies. International Journal of Human–Computer Interaction, 1-18. https://doi.org/10.1080/10447318.2024.2423335

[28] Soularidis, A., Kotis, K. I., & Vouros, G. A. (2024). Real-Time Semantic Data Integration and Reasoning in Life-and Time-Critical Decision Support Systems. Electronics, 13(3), 526. https://doi.org/10.3390/electronics13030526

[29] Suárez-Varela Macià, J. R. (2020). Enabling knowledge-defined networks: deep reinforcement learning, graph neural networks and network analytics

[30] Vankayalapati, R. K. (2020). AI-Driven Decision Support Systems: The Role Of High-Speed Storage And Cloud Integration In Business Insights. http://dx.doi.org/10.2139/ssrn.5103815

[31] Wu, D., Song, J., Bian, Y., Zheng, X., & Zhang, Z. (2021). Risk perception and intelligent decision in complex social information network. Industrial Management & Data Systems, 121(1), 99-110. https://doi.org/10.1108/IMDS-10-2020-0566

[32] Wu, W., Wen, C., Yuan, Q., Chen, Q., & Cao, Y. (2025). Construction and application of knowledge graph for construction accidents based on deep learning. Engineering, Construction and Architectural Management, 32(2), 1097-1121. https://doi.org/10.1108/ECAM-03-2023-0255

[33] Xiao, X., Liang, J., Tong, J., & Wang, H. (2024). Emergency decision support techniques for nuclear power plants: Current state, challenges, and future trends. Energies, 17(10), 2439. https://doi.org/10.3390/en17102439

[34] Yang, S., Zhang, Y., Lu, X., Guo, W., & Miao, H. (2024). Multi-agent deep reinforcement learning based decision support model for resilient community post-hazard recovery. Reliability Engineering & System Safety, 242, 109754. https://doi.org/10.1016/j.ress.2023.109754

[35] Zhang, D., Zhou, L., & Nunamaker Jr, J. F. (2002). A knowledge management framework for the support of decision making in humanitarian assistance/disaster relief. Knowledge and Information Systems, 4, 370-385. https://doi.org/10.1007/s101150200012

[36] Zhao, J., Xu, X., & Xiao, F. (2025). Aegis: A cloud-edge computing based multi-disaster crowd evacuation model using improved deep reinforcement learning. Computer Communications, 231, 108036. https://doi.org/10.1016/j.comcom.2024.108036

[37] Zhao, Z., Zhang, M., Chen, J., Qu, T., & Huang, G. Q. (2022). Digital twin-enabled dynamic spatial-temporal knowledge graph for production logistics resource allocation. Computers & Industrial Engineering, 171, 108454. https://doi.org/10.1016/j.cie.2022.108454