Action Recognition Certificates for Unbiased Process Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methodologies in manufacturing and other contexts face limitations due to incomplete and biased data sets from manual techniques, which hinder process optimization and quality improvement, especially with the growing demand for increased efficiency and accuracy in industries like manufacturing, healthcare, and retailing.
Innovation Solution
An action recognition and analytics system utilizing sensor streams from various sources, including video, thermal, and depth sensors, to automatically recognize cycles, processes, actions, and sequences, and create certificates for data sets, enabling more comprehensive and accurate data collection and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual techniques are used to gather data on human activity, then the implementation is simple and low-cost, but the data set is small, incomplete, and biased
Solution Approach 1:
The system uses a single comprehensive automated data collection platform that simultaneously captures multiple types of data (video, sensor readings, process information) across multiple workstations and contexts, replacing multiple separate manual collection methods with one multi-functional system
Solution Approach 2:
The patent replaces manual observation and data recording methods with automated electronic systems including video cameras, sensors, and software that automatically capture and store data without human intervention, eliminating the Hawthorne effect and Heisenberg effect inherent in manual collection
2Productivity
If the number of actions per station increases to accommodate growing demand, then productivity increases, but the cognitive load on operators increases resulting in higher deviation rates
Solution Approach 1:
The system continuously monitors operator actions and process parameters, providing real-time feedback and automated guidance to operators, which helps maintain consistent performance even as the number of actions per station increases, thereby preventing deviation rates from rising
Solution Approach 2:
The automated data collection and analysis system independently tracks and analyzes process deviations without requiring additional operator attention or decision-making, allowing operators to focus on executing actions while the system self-monitors for consistency
3Extent of automation
If IIoT devices are used to collect data from machines, then automation and data collection capability improve, but only a small portion of manufacturing tasks are covered
Solution Approach 1:
The system employs multi-functional sensors and cameras that can capture data across diverse manufacturing tasks and contexts, making the automated collection system adaptable to both machine-operated and manual tasks rather than being limited to specific equipment
Solution Approach 2:
The patent adds the dimension of visual and environmental sensing to traditional IIoT data collection, using video cameras and environmental sensors to capture information about operator actions and workspace conditions that complement machine sensor data, thereby expanding coverage across all manufacturing tasks
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 certificates for each instance of a subject product or service. The certificates can string together snippets of the sensor streams along with indicators of cycles, processes, action, sequences, objects, parameters and the like captured in the sensor streams.