Occupancy Cause Detection Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the cause of occupancy in predetermined areas, such as hospitals, are either invasive and costly or inaccurate and burdensome, lacking an automated and low-cost solution.
Innovation Solution
A computer-implemented method that utilizes real-time location information to generate occupancy information for zones within a predetermined area, processed using a machine-learning model to determine occupancy causes, which are events occurring within those zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a dedicated observer monitors the area using CCTV or in person to identify events, then the accuracy of determining occupancy causes is improved, but the cost and device complexity increase substantially due to additional staff and equipment overhead
Solution Approach 1:
The patent replaces the mechanical observation system (CCTV cameras and human observers) with an automated image processing system using machine learning models. The system captures images, processes them through trained ML models to detect events and identify occupancy causes, thereby eliminating the need for physical observers and reducing device complexity while maintaining high accuracy.
Solution Approach 2:
The system enables self-service monitoring by automatically analyzing images and determining occupancy causes without human intervention. The machine learning model autonomously processes visual data, identifies events, and generates occupancy cause determinations, making the system self-sufficient and eliminating the need for additional staff.
2Ease of operation
If members of staff log their reasons for occupying zones manually, then the burden on additional staff is reduced, but the accuracy decreases due to non-compliance or forgetfulness
Solution Approach 1:
The patent replaces the manual logging process with an automated image recognition system. Instead of relying on staff to remember and record occupancy reasons, the system uses machine learning models to automatically analyze images, detect events, and determine occupancy causes, thereby eliminating human error from non-compliance or forgetfulness while maintaining ease of operation.
3Device complexity
If manual logging by staff is implemented, then the need for additional monitoring equipment is reduced, but the time burden on users increases significantly
Solution Approach 1:
The system performs self-service monitoring by automatically capturing and analyzing images without requiring user action. The machine learning model processes visual data autonomously to determine occupancy causes, eliminating the time burden on users while keeping the system relatively simple compared to dedicated observer setups.
4Device complexity
If automated image processing with machine learning is used, then the cost and device complexity are reduced compared to dedicated observers, but the measurement precision may decrease without proper training data
Solution Approach 1:
The patent applies preliminary action by training the machine learning model in advance using labeled training data that includes images and corresponding occupancy cause information. This pre-training ensures the model achieves high measurement precision before actual deployment, resolving the contradiction between simplified device complexity and accurate event detection.
Data Source
AI summary
A method and system that enables a computer to determine a cause of occupancy of a predetermined area using real-time location information. The real-time location information is processed to determine occupancy information of each of a plurality of zones of the predetermined area. The (combined) occupancy information is processed using a machine-learning model to predict an occupancy cause of the predetermined zones of the predetermined area.