Distance-Weighted Workspace Allocation Using Occupancy Schedules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dynamic workspace allocation in buildings poses challenges in controlling the spread of infectious diseases due to unpredictable population densities and varying occupancy, making it difficult to manage HVAC equipment effectively and ensuring safe distancing among employees.
Innovation Solution
A method and system for generating workspace recommendations based on distance weights, occupancy schedules, and HVAC status, using machine learning and optimization algorithms to prioritize safe and efficient workspace assignments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If dynamic workspace allocation is implemented to accommodate employee convenience and preference, then workspace flexibility and employee satisfaction are improved, but control over population density and disease transmission risk deteriorates
Solution Approach 1:
The system performs preliminary actions by calculating optimal workspace assignments before employees arrive at the building. The optimization algorithm determines recommended workspaces in advance based on scheduled meetings, team collaborations, and safety distancing requirements, thereby preventing disease transmission risks before they occur while maintaining workspace flexibility.
Solution Approach 2:
The system introduces an intermediary optimization algorithm that mediates between employee workspace preferences and safety requirements. This algorithm acts as a mediator to balance flexible workspace allocation with disease transmission control by considering multiple factors including meeting schedules, team collaborations, and safe distancing constraints.
2Ease of operation
If workspace assignments are made based on personal convenience without considering occupancy patterns, then employee satisfaction is improved, but HVAC equipment optimization and energy efficiency deteriorate
Solution Approach 1:
The system implements feedback by continuously monitoring actual workspace occupancy patterns and comparing them with predicted patterns. This feedback loop enables the optimization algorithm to adjust HVAC equipment operation dynamically, ensuring energy efficiency while accommodating employee convenience and preference in workspace selection.
Solution Approach 2:
The system applies parameter changes by dynamically adjusting HVAC equipment settings based on optimized workspace assignments. The optimization algorithm determines appropriate temperature, humidity, and ventilation parameters for each workspace based on predicted occupancy, thereby improving energy efficiency while maintaining employee comfort and convenience.
3Reliability
If safe distancing constraints are enforced to reduce disease transmission risk, then employee safety is improved, but workspace availability and assignment flexibility deteriorate
Solution Approach 1:
The system applies dynamics by making safe distancing constraints dynamic rather than static. The optimization algorithm adjusts distancing requirements based on real-time factors such as ventilation quality, occupancy patterns, and meeting types, thereby maintaining employee safety while preserving workspace assignment flexibility and availability.
Solution Approach 2:
The system uses parameter changes by adjusting safe distancing parameters dynamically based on environmental conditions and occupancy patterns. The optimization algorithm modifies distancing constraints as needed to balance employee safety with workspace availability, allowing flexible assignments when conditions permit while maintaining safety when risks are higher.
Data Source
AI summary
A method for improved workspace recommendations according to distances between spaces. The method includes determining distances between a plurality of candidate workspaces and spaces of a building; assigning a first weight to distances between the plurality of candidate workspaces and occupied workspaces and a second weight to distances between the plurality of candidate workspaces and spaces of the building that are associated with a schedule of spaces in which a user will be located; determining a prediction score for a candidate workspace by aggregating a first sum of distances between the candidate workspace and the workspaces according to the first weight with a second sum of distances between the candidate workspace and the spaces that are associated with the schedule of spaces according to the second weight; and generating a recommendation assigning the user to the candidate workspace based on the prediction score.