Traffic Learning & Predictive Parking

With Compass Infinity, data from multiple sources such as touchscreen destination kiosks, eCall™ Pro smartphone information and integrated turnstile credential swipes are efficiently ingested and harmonically combined to feed state-of-the-art Machine Learning prediction algorithms.

The Compass Infinity destination management system continuously collects data and periodically uses the information to train algorithms. These algorithms adapt to changing traffic conditions generating accurate predictions. Months of traffic data are used to train models that predict future traffic throughout the day using time-related features such as time of day, day of week, and weekday/weekend/holiday information.

Traffic predictions are leveraged when an elevator becomes idle so it can be pre-parked to a floor where demand is expected to materialize.

This can reduce passenger wait time as much as 10% versus non-predictive methods.

Adaptive Parameters Tuning (APT)

Compass Infinity AI technology tunes elevators without human intervention. Algorithms are driven from the data, and parameters tune according to specific traffic patterns observed at the building.

AI technology can tune multiple sets of dispatching parameters to accommodate different customer preferences during critical traffic periods.

This technology can significantly improve dispatching performance during peak hours.

We have observed as much as 20% average wait time reduction versus our non-AI dispatcher.