AI System for Office Occupancy, HVAC and Lighting Decision Support

The problem

In day-to-day operations, differences between calendars and actual occupancy can lead to unnecessary energy use. When anonymous occupancy counts, room bookings, working hours, indoor conditions, outdoor conditions, HVAC status and lighting status are scattered across sensors, documents, field records or team files, issues may not become visible in time.

This fragmented data delays preparation of zone-level HVAC and lighting suggestions and forces teams to search manually for supporting evidence again. The facilities manager or building energy engineer must complete missing records and verify each conflict before making a decision.

A common exception is that events, cleaning, accessibility requirements or indoor-air needs may make an apparently empty area active. Incomplete or incorrect automation that fails to check this context could compromise employee comfort, indoor air quality or safe access, so no physical or operational action can be carried out directly.

What we set out to improve

• Proportion of zone-setting suggestions accepted by the facilities manager
• Proportion of outputs corrected or rejected by the facilities manager or building energy engineer
• Time between the source event and the review output

How the system works

1. 01 Define the review scope and the role of the authorised facilities manager or building energy engineer
2. 02 Retrieve the inputs: anonymous occupancy counts, room bookings, working hours, indoor conditions, outdoor conditions, HVAC status and lighting status
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Check occupancy data recency and zone assignment
5. 05 Prepare options using bookings, weather conditions and current settings
6. 06 Check for exceptions: events, cleaning, accessibility requirements or indoor-air needs may make an apparently empty area active
7. 07 Place low-confidence or conflicting records in a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the facilities manager or building energy engineer approve, correct, defer or reject the output

Methods we used

• Zone-level constraints and comfort limits without person recognition
• Source, format, timing and required-field checks for anonymous occupancy counts, room bookings, working hours, indoor conditions, outdoor conditions, HVAC status and lighting status
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• A separate exception check outside the main rule
• Combined retention of the source, rule result, zone-level HVAC and lighting suggestions and human decision

Where people stay involved

Data and security

Access to anonymous occupancy counts, room bookings, working hours, indoor conditions, outdoor conditions, HVAC status and lighting status is restricted to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary portion of the dataset is sent to the model. Access, outputs and the facilities manager or building energy engineer's decision are logged; production use does not begin until the organisation has approved the retention period and data location.

Who this suits

Frequently asked questions