Exploring AI-Enhanced Incident Management and Reporting for Firefighters

Client

Redlab.ai

Role

Product Designer (UX Lead)

Project details

Timeline: January 2023 - Present

Team:

Problem

Writing incident reports for firefighters is not only time-consuming but also error-prone.

It considerably increases their work stress, which has an adverse effect on their psychological well-being and job performance.

Underlying Issue: Outdated reporting system

Its lengthy forms necessitate extensive responses. How much the firefighter remembers determines the report's accuracy. Inaccuracies can lead to legal consequences and reputational risks.

Solution

Advanced Incident Reporting System. Leverages deep learning and natural language processing (NLP) to analyze raw radio incident data, automatically extracting key details and summarizing the incident.

Generates a high-quality draft report, saving firefighters time and ensuring consistent reporting. After reviewing and making any necessary edits, firefighters can submit the final report with ease.

Opens doors to endless possibilities to leverage incident data for diverse report generation, performance enhancement, anomaly detection, etc.

Project Overview

(2 mins) Everything you need to know about this project.

Impact

Project Scope:

+ 50 %

User interviews with 8 firefighters revealed this could accelerate their incident report generation by at least

Individual Impact:

+ team expansion

Led to addition of the data science team, to further research and develop the concept MVP

Proof of Concept

01 Advanced incident management dashboard

Integrating all-in-one cohesive enterprise solution

Personalize your workspace with widgets that deliver real-time analytics, putting crucial information at your fingertips.

02 New incident reporting flow

Simplified workflow and amplified efficiency

Optimized NFIRS user flows, ensuring intuitive navigation and minimal disruption.

03 Firegen: AI integration

AI automation for precise & swift incident documentation

Analyzing raw radio data, the system automatically extracts essential information, auto-populates, and creates a draft report. Firefighters can then swiftly validate and submit the draft, streamlining the reporting process with accuracy and efficiency.

04 Keyword-based data categorization

Introducing novel keyword categorization

We classified incident transcript data into five key categories:

Identifiers (e.g., "Street; Intersection; Incident");
‍Extraction Data (e.g., "West Michigan St.");
‍Sectional Keywords (e.g., "Arrived at location");
‍Metadata (e.g., fire department details); and
‍Filler Data (anything that cannot be classified or situational content).

This structured approach enhances data processing efficiency, ensuring vital information is accurately extracted for streamlined reporting.

Project Status

Currently our multidisciplinary UX and data science teams are collaboratively addressing domain-specific challenges in the tool development.

We are focusing on efficiently training state-of-the-art models to process raw incident radio data. We are collaborating with the Indy Fire Dept. to create incident datasets from real data after masking and scrubbing. I developed the prototype and am testing it with firefighters and subject matter experts (SMEs).

Present Key objectives

Design validation and identify specific user needs within this integrated platform

Studying users (firefighters) psychology—How do they use/interact with the product prototype?

Curious about the journey? Let’s dive deeper

This showcase is merely a glimpse; the true essence lies in the journey itself. If you're intrigued, let's chat—I’ll happily share insights, challenges, and even some juicy gossip from behind the scenes.

Let’s talk