Introduction : In today’s fast-paced world, businesses must prioritize cleanliness to create a positive and welcoming environment for employees, customers, students residents and patients alike. Companies rely on their in-house cleaning staff or commercial cleaning services to ensure the highest standards of cleanliness. How can employers ensure that cleaning is done on time with the required standards? Although there are operational practices in place to manage quality of cleaning, what if AI could help in tracking cleaning time and measure performance metrics? Operational improvements like staff rotation or schedule adjustments need to be measured before and after to ensure facility managers are moving in the right direction. Corporate actions like standardization of outcomes and cost will need help from AI to track and publish data for efficient execution.
Value of cleaning v/s usage data: Facilities supervisors create schedules and select team members for specific tasks. The expected outcomes are on time cleaning with all the spaces cleaned per schedule. Having real time and historical data on this compliance can help supervisors modify schedules, swap cleaning vendors and most importantly prioritize and rotate spaces on priority to get cleaned. To determine the priority, having foot traffic and space usage data is extremely useful. If an area sees a lot of foot traffic and/or sees animal traffic like dogs etc, cleaning priority is high when compared to spaces with minimal usage since the last clean. Schedules can be more agile while keeping new resource allocation to a minimum
Actionable technology to track cleaning along with foot traffic
Tracking cleaning can be done by training AI to recognize a combination of Cleaning equipment (Buckets, carts, vacuums and mops), staff uniform (if available) and movement patterns in the spaces. Cleaner movements can be tracked over the space of the room to ascertain the cleaning coverage and the time spent in cleaning. This tech can be made actionable when actual cleaning is compared to the planned schedule. This compliance can be measured week over week while counting the spaces that were missed on given days. If cleaning needs to happen before, say 10 AM everyday, compliance can be tracked to measure effectiveness.
Moii’s Solution: Moii has evolved AI cleaning tracking to work with any commercial cameras that you have already invested in and run our patent pending machine learning pipeline that is geared towards extracting necessary context for cleaning data. This, when combined with our industry leading data science algorithms, provides reports to facility management on their cleaning metrics. Space usage or foot traffic is overlaid on the cleaning compliance to give a big picture view of which room should still be uncleaned. For example, if a room has not been cleaned and the foot traffic was high, this room can be prioritized over a room where the foot traffic was low and not cleaned yet. Late cleaning can also be tracked independently or in conjunction with the schedule to explore various ideas for new schedules and team rotation. This data can integrate through API into scheduling systems or other facilities management software to get enterprise level benefits of this technology.
What to expect in terms of results?
Our customers now have reports that track cleaning compliance overlaid with space usage on a daily/weekly basis. By combining this information with schedule and team information, rich insights and metrics were tracked. If a specific, highly used space was rarely cleaned on time, the schedule was altered so as to have the team start with that space first for a week. For spaces that were not cleaned at all, staff adjustments were made and the weekly compliance was tracked post changes. This improved accountability of commercial cleaning services. The usefulness of video is clear as its definite proof of actions in the case of late cleaning.All such processes resulted in compliance going from 30-40% range to a 90+% range within 6-8 weeks post technology install. The ability to plug and play technology to existing cameras allowed for speedy decision making and with a low cost solution that learns over time and gets smarter on actual cleaning actions.
