StockView for Healthcare
Reduce the duration of critical medical supplies out of stock with AI-powered stock out detection
StockView uses customized AI models running locally, at the edge of the cloud, to detect missing products visually. It then enables providers to build powerful analytics across locations, regardless of the quality of their internet access or the number of supply locations.
Powered by Microsoft Azure Stack Edge, StockView offers a scalable and cost-effective solution that leverages the power of the Azure cloud platform at the facility level. It provides an easy to predict TCO via a fixed per-month and per-device cost business model, regardless of the number of video streams and other locally deployed containerized services.
Benefits
Reduce out-of-stock by ensuring prompt restocking
Combine data from multiple medical supply closets to adapt supply-chain to real-time needs
Use AI running at the edge to scale across your supply closets cost-effectively and predictably
Ensure prompt medical supplies restocking
Medical personnel is wasting precious patient-caring time managing out-of-stock in medical supply closets. StockView uses AI-powered shelf void detection technology to reduce these out-of-stock incidents.
With near real-time out-of-stock detection, StockView enables notifications to be proactively sent to the appropriate systems and people to ensure medical personnel does not have to manage it themselves.
With Neal Analytics’ out-of-the-box apps, dashboard, and automation tools, hospital pharmacies can react more quickly and reduce negative impacts on patient care due to missing key medicine or equipment.
Consolidate data across supply closets to improve supply chain
Pharmacy administrators and hospital managers can consolidate data from multiple supply closets to optimize restocking based on each department’s unique usage patterns.
Using consolidated data across locations, data can also help spot trends and reduce system-wide out-of-stock incidents by tuning the location or group-level supply chain.
Over time, when enough historical data is available, granular predictive models can also be built to help prevent out-of-stock incidents.
Cost-effectively scale with AI at the edge
StockView is built on the flexible and powerful Azure Stack Edge device. Once models are trained on the Azure cloud, they are deployed in the device. These AI models will use AI-powered image processing algorithms to detect empty spaces on a shelf. This means that no specific shelf technology is required, and StockView can be deployed in virtually any supply closet.
Because the box is located at the closet or building level, it does not require high-definition video streaming to the cloud. This makes it a more reliable, cost-effective, and scalable solution.
This distributed approach also allows customers to scale at their own pace, starting with proofs-of-concept using a single device in one location to as many as necessary to cover all the needs.
