Seattle Police Department employs advanced AI to assist dispatchers in rapidly and accurately categorizing incoming calls.
Overview
The Digital Transformation Hub at Cal Poly (DxHub), in collaboration with Amazon Web Services (AWS) has partnered with the Seattle Police Department to develop an innovative React web application that displays, in near real-time, the most probable police response category out of four possible options. The solution streamlines the process of categorizing incoming calls by assisting call takers to enable faster and more accurate responses to emergencies and ease the mental burden experienced by call takers.
Problem
Dispatchers at emergency call centers face the critical task of quickly and accurately categorizing incoming calls to ensure appropriate and timely police responses. Misclassification or delays in determining the correct response category can have serious consequences. The Seattle Police Department sought a innovative solution that would assist dispatchers in making rapid, data-driven decisions by leveraging advanced AI technologies to analyze the caller’s spoken words in real-time.
Innovation in Action
The DxHub team, in collaboration with Loren Atherley, Seattle Police Department’s Director of Performance Analytics & Research and Accenture the DxHub team focused on how we could bring this concept to implementation through a rapid prototyping process that was focused on demonstrating iterative demos that attempted to illustrate the set of technical possibilities. Through interviews with call center team, the DxHub team was able to understand current needs and translate that into potential deliverable assets. This foundational work informed the design of the web application, ensuring alignment with the real-world requirements of emergency response teams.
Technical Solution
A React web application was developed by the DxHub team that utilizes a custom-trained classifier powered by Amazon Comprehend. As the caller speaks, their words transcribed and speakers are separated into caller and call taker using Amazon Transcribe. The words are then sent to the AWS cloud and placed into a DynamoDB table which is triggered by a Lambda function that sends the callers progressive conversation into the classifier. This classifier takes the increasing set of spoken words and analyzes the language and generates probabilistic responses for each of the four predefined categories. These oscillating probabilities are displayed graphically to the user, with each category accompanied by a relevant image that reflects the quantitative value.
As more words are spoken, the model tracks historical trends, progressively refining its predictions towards a likely outcome. To determine the stability of the response, a statistical approach based on the number of standard deviations (z-score) of each successive probabilistic outcome is employed. Once the response is deemed stable, the web application prominently displays the most likely category along with any relevant standard operating instructions for that response type.
The custom classifier, primarily developed by Accenture, leverages the power of Amazon Comprehend to accurately analyze the larger set of words spoken by the caller. By passing these words through the classifier, the application obtains probabilistic responses for each category, enabling real-time decision support for the dispatchers.
This innovative solution combines the strengths of React web development, AI-powered language analysis, and data visualization to enhance the efficiency and accuracy of emergency response categorization. By providing dispatchers with real-time, data-driven insights, the Seattle Police Department can optimize resource allocation, reduce response times, and ultimately improve public safety outcomes.
About the DxHub
The Cal Poly Digital Transformation Hub (DxHub) is a strategic relationship with Amazon Web Services (AWS) and is the world’s first cloud innovation center supported by AWS on a University campus. The primary goal of the DxHub is to provide real-world problem-solving experiences to students by immersing them in the application of proven innovation methods in combination with the latest technologies to solve important challenges in the public sector. The challenges being addressed cover a wide variety of topics including homelessness, evidence-based policing, digital literacy, virtual cybersecurity laboratories and many others. The DxHub leverages the deep subject matter expertise of government, education and non-profit organizations to clearly understand the customers affected by public sector challenges and develops solutions that meet the customer needs.