Patrol – it’s the backbone of every department. But command staff must assess whether patrol resources are consistently deployed in a data-driven way.
Does uncommitted patrol time take into account constantly changing environmental factors and trends that can impact the likelihood of where crime occurs and when?
Patrol Management Software
Patrol management software uses artificial intelligence-driven analysis to help strategically plan patrol missions
and tactics for maximum crime deterrence
Planning Patrol Time
- The system provides patrol officers with a forecast of the highest risk areas for crime that the agency is prioritizing. Boxes represent a precise area (250 meters by 250 meters) for patrol and are color coded by crime type
- When officers arrive in the box, the mission officially begins and a configurable timer starts so that the area is not over or under patrolled
- Authorized users such as crime analysts can add or suppress a mission based on new information
- The mission can be viewed on an MDT, smartphone, desktop or printed out
- [New] ShotSpotter Missions now uses historical and continuously updated ShotSpotter gunfire data to create enhanced gunfire forecasts since only 20% of gunfire is reported by the community
The agency selects which crime types to forecast and weights each based on priorities. Mission duration and suggested tactics are configured. Local district maps with beat boundaries are created. Data from CAD and RMS are input into the model.
Training the Model
The system is “trained” using machine learning based on the agency’s event data along with temporal, geospatial, and census data. The model is then tested against recent crime data to calibrate forecast accuracy.
Once trained and tested, the model produces daily shift-by-shift recommended missions that sends officers to the most likely locations for crime.