Quantifying Police Interactions (QPI) Title: Quantifying Police Interactions (QPI) Unmet Need: Underutilization and restriction to the Body Worn Cameras (BWC) hampers review rates, hindering intelligence gatherings and evidence identification. The limited access to BWC footage, with existing software only permitting officers to view it, has resulted in less than 5% of recordings being reviewed by police agencies. The underutilization hinders the potential of BWC footage to gather intelligence and serve as valuable evidence in discovering important information. A team of Inventors has developed software named QPI (Quantifying Police Interactions), a web-App that is capable of viewing and labeling objectively police BWC footage, utilizing both manually and automatically. This software collects, analyzes, and displays data to facilitate department reflection focusing on service oriented rather than prioritizing profit. The Technology: Improved performance of web application by increasing the level of efficiency at gathering data from incidents. The invention developed a web application that assists police departments providing evidentiary value, identifying strengths and weakness within the agency. This user interface allows for quick labeling of events that take place during recorded police BWC footage. Applications: Enhanced evidence management and organization Improved training tool for police officers and department reflection Promote public trust and community relations by demonstrating unbiased approach Potentially improve local, state, and federal laws Advantages: Speeds up the user’s workflow Access to the most modern tools Maintainability for future teams Seamless deployment of new versions Integration with existing systems Patent Information: Provisional patent application has been filed. Learn More Scott Steiger Associate Director Washington State University (509) 335-7065 scott.steiger@wsu.edu Reference No: TECH-23/3492 Bookmark this page Download as PDF Inventors David Makin Dale Willits Mantz Wyrick Peyton Urquhart Lucas Da Silva Zachary Barnett Megan Parks Key Words Machine Learning Risk Monitoring Supervision