Automated Work Charting With Action Recognition for Human Process Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methodologies for process optimization in manufacturing, such as Lean Manufacturing and Six-Sigma, rely on manual data collection which is incomplete, biased, and delayed, failing to provide comprehensive insights into human activities and processes.
Innovation Solution
An automated work charting system using action recognition and analytics, which processes sensor streams from various sources to identify cycles, processes, actions, sequences, objects, and parameters, creating a data structure for indexing and analyzing these elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If manual techniques are used to gather data on human activity, then data collection is simple and low-cost, but the data set is small, incomplete, and biased
Solution Approach 1:
The patent replaces manual data collection methods with automated computer vision and machine learning systems. Sensors capture video and sensor data that are automatically processed by algorithms to detect actions, processes, and cycles, eliminating the need for manual observation and recording while providing comprehensive, unbiased data sets
Solution Approach 2:
The patent introduces sensors and computer vision systems as intermediaries between human operators and data analysis. These intermediaries automatically capture and transmit data about human activities, processes, and environmental conditions, enabling continuous monitoring without direct human intervention in the data collection process
2Productivity
If the number of actions per station increases, then productivity is improved, but the cognitive load on the operator increases resulting in higher deviation rates
Solution Approach 1:
The patent implements real-time feedback systems where sensors and computer vision continuously monitor operator actions and provide immediate feedback on deviations from standard procedures. This allows operators to correct errors instantly and enables management to identify training needs, maintaining high reliability even as productivity increases
Solution Approach 2:
The system enables self-service through automated work charts that dynamically adjust based on real-time data. The system automatically identifies bottlenecks, suggests process improvements, and provides contextual information to operators, reducing cognitive load while maintaining or increasing productivity
3Extent of automation
If IIoT devices are used to collect data, then automation is improved, but the data set remains incomplete as machines only perform a small portion of tasks
Solution Approach 1:
The patent creates a universal data collection system that monitors both machines and human operators using the same sensor infrastructure and analytical platform. This multi-functional approach captures data across the entire value stream, including human actions, machine operations, environmental conditions, and process parameters, providing a complete data set that reflects the full complexity of manufacturing operations
Data Source
AI summary
The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for automatic creation of work charts.