Swedish telecoms operator Telia has developed a video-recognition application to improve efficiency and accuracy at Finnish logistics operator Transval. The application depends on a virtual private 5G network and AWS edge computing. Since implementation, it has replaced the need for manual physical inventory counts and reconciliation by automatically tracking and reporting on movement of inventory.

The project started as a proof of concept in an outsourced warehouse managed by Transval on behalf of one of its customers. HD cameras were connected via a virtual private network to Telia’s data centre in Helsinki, using Amazon SageMaker to build, train and deploy a machine learning model to recognise customer-specific pallets and track their movement in and out of the production buffer maintained by Transval on behalf of its customer. The buffer is used to adjust for variations in the production process, ensuring that the production line continues to run smoothly.

According to Telia, it could not have developed the solution if it had not invested in its 5G and modernised 4G networks, as well as in upskilling 10% of employees on Amazon Web Services and cloud technologies to enable faster innovation cycles and meet new customer demands.

The ML model calculates the number of pallets in a given area, reports how much free space is left in each stack and tracks the movement of pallets from one stack to another, revealing an accurate picture of inventory levels in real time. Previously, this was a manual process characterised by counts and recounts that was prone to human error.

Telia created an application programming interface that Transval used to develop an application that has been installed on its mobile devices, enabling employees to easily receive alerts from the ML model while moving around the warehouse. By ensuring that inventory counts match the actual amount of inventory in the warehouse, the ML model prevents shortages that could otherwise bring the customer’s production line to a halt.

Enterprises have been focused on creating a differentiated end-user experience by harnessing data generated by customers and IoT devices. By harnessing AWS services and the AWS ISV Accelerate Program, Telia is able to help enterprises build such end-user applications in-house. In addition, through AWS Outposts, as well as AWS Local Zones and Availability Zones, these applications can extend from the cloud to the factory floor while leveraging Telia’s high-capacity, high-speed 5G networks. By standardising the development of this new solution for Transval, Telia will enable other customers to achieve improved levels of automation and production optimisation and accelerate the adoption of future ultra-low-latency use cases.

Rainer Deutschmann, Group Chief Operating Officer at Telia Company, said: “Our collaboration with AWS to deploy our private networks offering combined with the cloud delivers simplicity, improved operational efficiency and the opportunity to quickly develop new initiatives to meet market needs. It’s about achieving scale and prioritising security while reducing complexity, to the benefit of our customers and, ultimately, end users in our markets.”

Fabio Cerone, Managing Director for the EMEA telco industry at AWS, said: “Real-time and high-fidelity experiences like warehouse logistics and supply chain require security and low latency. Leveraging AWS edge services and machine learning services, Telia was able to build, deploy, and manage a ML model and tailored private network to support Transval’s real-time needs. This is an example of how AWS is supporting communication services providers to leverage their 5G networks and expertise to deliver new value to their customers.”

Riku Koskimaa, Senior Manager of Business Development at Transval, said: “The solution developed by Telia and powered by AWS has increased our ability to access real-time information about buffer inventory levels in our warehouse. As a result, it has become much easier to ensure that our delivery buffer levels are as agreed with our customer and according to our KPI targets. By visually tracking buffer levels and providing real-time updates, we ensure that our customers have the items they need in their buffers at all times.”