During the pandemic, businesses were struggling with the dilemma of reopening their sites and trying to return to normal levels of operation, without compromising the safety of staff and customers.
Just hoping that things will be okay was not a viable strategy. If measures were not taken to reduce the risk of infection, businesses that reopen were likely to end up in a vicious circle of reduced operations due to staff sickness and reputational damage amongst risk averse customers.
But any approach that is too cautious does not benefit businesses either. If all staff were sent home when one gets sick, it would reduce their risk, but effectively shut down the firm.
Introducing Safe at Work
Safe at Work, developed in partnership with Canadian technology firm, Sightline Innovation, uses a variety of sensing technologies to build a spatio-temporal database of which individuals were in the same space at the same time.
Everytime a sensor detects a person, it records their presence. But the graph database that is generated could be used to describe much more than just a headcount. It can reveal valuable insights about how a space is being used - the patterns of behaviour that could either increase or reduce the risk to staff and customers.
In an ideal situation, staff would enter a facility in an orderly and socially distanced way, making their way to a workstation with minimal contact with team members.
Normal patterns of movement / behaviour are much less controlled and consequently more likely to increase risk. If operations leaders were able to visualise the ebb and flow of people throughout the day, it would become easier to target specific interventions to reduce this risk.
The Elephant in the room (for 17 minutes from 08:56)
Whilst modelling the precise movements of people around a facility will provide valuable insights about overall behaviour, it clearly comes with privacy concerns.
Taking inspiration from Nathan Yau’s A Day in the Life of Americans alternative visualisation approaches could be explored that provide a level of abstraction that anonymises the movement patterns of individuals - instead aggregating them by teams, zones, floors etc.
Our early explorations used anonymised dots to denote individuals moving around the space. But even without names attached to them, it would still be relatively trivial to establish who a dot represented, based on where they returned to - or spent the majority of their time.
Instead, by focusing on abstracted paths between points and the volume of traffic along them, a greater level of privacy enhancement was achieved. This visualisation approach had the added benefit of providing a better view for spatial analysis and intervention planning. Accompanying contact tracing functionality could then be used for when facilities teams needed to know the specific individuals at risk.