An official website of the United States government
Emergency response services are critical to public safety, with 9-1-1 call-takers playing a key role in ensuring timely and effective emergency operations. To ensure call-taking performance consistency, quality assurance is implemented to evaluate and refine call-takers' skillsets. However, traditional human-led evaluations struggle with high call volumes, leading to low coverage and delayed assessments. We introduce LogiDebrief, an AI-driven framework that automates traditional 9-1-1 call debriefing by integrating Signal-Temporal Logic (STL) with Large Language Models (LLMs) for fully-covered rigorous performance evaluation. LogiDebrief formalizes call-taking requirements as logical specifications, enabling systematic assessment of 9-1-1 calls against procedural guidelines. It employs a three-step verification process: (1) contextual understanding to identify responder types, incident classifications, and critical conditions; (2) STL-based runtime checking with LLM integration to ensure compliance; and (3) automated aggregation of results into quality assurance reports. Beyond its technical contributions, LogiDebrief has demonstrated real-world impact. Successfully deployed at Metro Nashville Department of Emergency Communications, it has assisted in debriefing 1,701 real-world calls, saving 311.85 hours of active engagement. Empirical evaluation with real-world data confirms its accuracy, while a case study and extensive user study highlight its effectiveness in enhancing call-taking performance.
more »
« less
This content will become publicly available on April 11, 2026
Sim911: Towards Effective and Equitable 9-1-1 Dispatcher Training with an LLM-Enabled Simulation
Emergency response services are vital for enhancing public safety by safeguarding the environment, property, and human lives. As frontline members of these services, 9-1-1 dispatchers have a direct impact on response times and the overall effectiveness of emergency operations. However, traditional dispatcher training methods, which rely on role-playing by experienced personnel, are labor-intensive, time-consuming, and often neglect the specific needs of underserved communities. To address these challenges, we introduce Sim911, the first training simulation for 9-1-1 dispatchers powered by Large Language Models (LLMs). Sim911 enhances training through three key technical innovations: (1) knowledge construction, which utilizes archived 9-1-1 call data to generate simulations that closely mirror real-world scenarios; (2) context-aware controlled generation, which employs dynamic prompts and vector bases to ensure that LLM behavior aligns with training objectives; and (3) validation with looped correction, which filters out low-quality responses and refines the system performance. Beyond its technical advancements, Sim911 delivers significant social impacts. Successfully deployed in the Metro Nashville Department of Emergency Communications (MNDEC), Sim911 has been integrated into multiple training sessions, saving time for dispatchers. By supporting a diverse range of incident types and caller tags, Sim911 provides more realistic and inclusive training experiences. In our conducted user study, 90.00 percent of participants found Sim911 to be as effective or even superior to traditional human-led training, making it a valuable tool for emergency communications centers nationwide, particularly those facing staffing challenges.
more »
« less
- Award ID(s):
- 2427711
- PAR ID:
- 10627100
- Publisher / Repository:
- Association for the Advancement of Artificial Intelligence
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 39
- Issue:
- 27
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 27896 to 27904
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper presents employee perspectives from two German water and wastewater utilities regarding their involvement in providing water and wastewater services for displaced persons in urban emergency accommodations. In 2015, 28 European countries received over two million applications for asylum, almost three times more than the previous year. According to the UNHCR, this rapid increase in population has reached the highest recorded displacement in the world’s history, even greater than that proceeding the Second World War. The German utilities are meeting these new demands; however, we lack knowledge regarding the impacts on the utilities as they provide water and wastewater services to the suddenly increased population. As a result of this gap, this study looks at how water and wastewater utilities perceive their involvement in this process and in what ways they legitimize their provision of water and wastewater services to displaced persons. Understanding this legitimation equips both utilities and other stakeholders to better understand how utilities regard their role in urban emergency response. Results show that individuals use their past experience (comprehensibility legitimacy) and understanding of socially acceptable technical processes (procedural legitimacy) to legitimize their role in the crisis organization. Comprehensibility legitimacy is used to express certainty in managing the technical challenges of providing water and wastewater services, while procedural legitimacy is used to justify improvisation to navigate gaps in design and construction guidelines for water and wastewater connections. Implications of this study suggest that although employees are confident in their ability to handle the situation, there are also opportunities for improving response in the future, such as creating more technical guidance for design water and wastewater connections for displaced persons in renovated buildings and new developments.more » « less
-
ObjectiveWe aimed to identify opportunities for application of human factors knowledge base to mitigate disaster management (DM) challenges associated with the unique characteristics of the COVID-19 pandemic. BackgroundThe role of DM is to minimize and prevent further spread of the contagion over an extended period of time. This requires addressing large-scale logistics, coordination, and specialized training needs. However, DM-related challenges during the pandemic response and recovery are significantly different than with other kinds of disasters. MethodAn expert review was conducted to document issues relevant to human factors and ergonomics (HFE) in DM. ResultsThe response to the COVID-19 crisis has presented complex and unique challenges to DM and public health practitioners. Compared to other disasters and previous pandemics, the COVID-19 outbreak has had an unprecedented scale, magnitude, and propagation rate. The high technical complexity of response and DM coupled with lack of mental model and expertise to respond to such a unique disaster has seriously challenged the response work systems. Recent research has investigated the role of HFE in modeling DM systems’ characteristics to improve resilience, accelerating emergency management expertise, developing agile training methods to facilitate dynamically changing response, improving communication and coordination among system elements, mitigating occupational hazards including guidelines for the design of personal protective equipment, and improving procedures to enhance efficiency and effectiveness of response efforts. ConclusionThis short review highlights the potential for the field’s contribution to proactive and resilient DM for the ongoing and future pandemics.more » « less
-
The problem of dispatching emergency responders to service traffic accidents, fire, distress calls and crimes plagues urban areas across the globe. While such problems have been extensively looked at, most approaches are offline. Such methodologies fail to capture the dynamically changing environments under which critical emergency response occurs, and therefore, fail to be implemented in practice. Any holistic approach towards creating a pipeline for effective emergency response must also look at other challenges that it subsumes - predicting when and where incidents happen and understanding the changing environmental dynamics. We describe a system that collectively deals with all these problems in an online manner, meaning that the models get updated with streaming data sources. We highlight why such an approach is crucial to the effectiveness of emergency response, and present an algorithmic framework that can compute promising actions for a given decision-theoretic model for responder dispatch. We argue that carefully crafted heuristic measures can balance the trade-off between computational time and the quality of solutions achieved and highlight why such an approach is more scalable and tractable than traditional approaches. We also present an online mechanism for incident prediction, as well as an approach based on recurrent neural networks for learning and predicting environmental features that affect responder dispatch. We compare our methodology with prior state-of-the-art and existing dispatch strategies in the field, which show that our approach results in a reduction in response time with a drastic reduction in computational time.more » « less
-
null (Ed.)The number of emergencies have increased over the years with the growth in urbanization. This pattern has overwhelmed the emergency services with limited resources and demands the optimization of response processes. It is partly due to traditional ‘reactive’ approach of emergency services to collect data about incidents, where a source initiates a call to the emergency number (e.g., 911 in U.S.), delaying and limiting the potentially optimal response. Crowdsourcing platforms such as Waze provides an opportunity to develop a rapid, ‘proactive’ approach to collect data about incidents through crowd-generated observational reports. However, the reliability of reporting sources and spatio-temporal uncertainty of the reported incidents challenge the design of such a proactive approach. Thus, this paper presents a novel method for emergency incident detection using noisy crowdsourced Waze data. We propose a principled computational framework based on Bayesian theory to model the uncertainty in the reliability of crowd-generated reports and their integration across space and time to detect incidents. Extensive experiments using data collected from Waze and the official reported incidents in Nashville, Tenessee in the U.S. show our method can outperform strong baselines for both Fl-score and AUC. The application of this work provides an extensible framework to incorporate different noisy data sources for proactive incident detection to improve and optimize emergency response operations in our communities.more » « less
