System to Predict Code Quality Profile Using Biometric Wearables and Smart Environment IOT Devices
Publication Date: 2017-Jun-21
The IP.com Prior Art Database
Disclosed is a system that monitors a user’s wearable Internet of Things (IOT) devices
to determine whether the user is performing tasks under optimal conditions. If conditions
indicate that the user’s quality of work might suffer, then the system issues an alert to
System to Predict Code Quality Profile Using Biometric Wearables and Smart Environment IOT Devices Disclosed is a system that monitors a user’s wearable Internet of Things (IOT) devices to determine whether the user is performing tasks under optimal conditions. If conditions indicate that the user’s quality of work might suffer, then the system issues an alert to the user. Environmental and biological factors can influence the quality one's work. To predict work quality and avoid costly rework, a method is needed to correlate any number of factors with the quality of one's work to provide a warning or trigger a review process. The novel solution is a system that relates data from Internet of Things (IOT) devices (e.g., wearable biometric sensors, environmental sensors, etc.) with the tasks performed at the time the IOT device records the data. The system uses this correlated data to build a predicted quality profile of the tasks performed based on measurable historic quality from similar correlated IOT and task data points. The core points of novelty include the system’s ability to:
Connect IOT devices/wearable biometrics with quality of development work Build a profile of IOT data points when quality is poor Connect IOT data timepoints with the type of work that the user is performing at
that time Trigger quality warnings when IOT data indicates conditions that correlate with
past instances of poor work By creating alerts and notifying the user of the best conditions (e.g., room temperature, lighting, standing, not standing, etc.) for optimal performance, the system prevents users from performing certain tasks under conditions that might hinder the quality of the product or action. For example, the system can prevent developers from coding under high amounts of mental stress. This system has several dependent parts:
IOT data: Gathered data from IOT/wearable devices Development environment data: Gathered task data from hosted/cloud
development environment Quality data: Gathered quality data from hosted/cloud development/
Collaborative Lifecycle Management (CLM) environment Machine learning: Correlated data (from previous steps) through a cognitive
analytics system to identify IOT data points that correlate to the time of the performed task (e.g., when code was written) to the associated quality data identified from hosted/cloud/CLM systems. This builds a dataset of IOT data points that may predict poor quality work.
Code Quality Prediction: Use the previous component’s dataset to alert the user on the cloud/hosted development environment when said user is working under
poor code quality conditions,...