Sim911: Towards Effective and Equitable 9-1-1 Dispatcher Training with an LLM-Enabled Simulation

2024-12-22

AI Summary

Traditional 9-1-1 dispatcher training suffers from incomplete coverage, high labor intensity, and poor adaptability to vulnerable populations. To address these limitations, we propose the first large language model (LLM)-driven simulation training system specifically designed for emergency dispatchers. Our method integrates three core innovations: (1) a domain-specific knowledge base constructed from real-world 9-1-1 call transcripts; (2) context-aware, controllable dialogue generation; and (3) response quality verification with a human-in-the-loop feedback mechanism. The system combines vector-based retrieval, dynamic prompt engineering, historical call modeling, multilingual support, and low-resource community adaptation. Experimental results demonstrate significant improvements in training fidelity, scalability, and equity—enabling high-fidelity, customizable simulations across diverse emergency scenarios. This work establishes a reusable technical paradigm for public safety communications training.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

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.

Problem

• 9-1-1 operator training
• efficiency
• comprehensiveness

Innovation

• Large Language Model
• Simulated Training
• Quality Assessment