U.S. Postal Service (USPS) has deployed advanced computer systems at 195 mail processing centres nationwide to apply seven computer vision models, cutting the time it takes to track a missing package from several days to less than two hours. Additionally, a computer vision task that would have taken two weeks on servers with 800 CPUs can be done in 20 minutes on four high-end graphics processing units.
The agency uses the Edge Computing Infrastructure Program (ECIP), a distributed Artificial Intelligence (AI) system. Each edge server processes 20 terabytes of images a day from more than 1,000 mail processing machines. The Triton Inference Server, an open-source software, provides the AI models each of the mail processing centres need.
Thirteen EGX systems run in two data centres and train the seven algorithm USPS has built so far. The overall design is to continue to enhance and build a database for packages so that they can over time improve package processing and efficiency and build from this model. The project began about a year ago and USPS is already working on additional applications. For instance, it put out a request for one that uses optical character recognition (OCR) to streamline imaging workflow.
The OCR use case will live as a deep learning model in a container on ECIP and served by the software capabilities that help organisations manage the deployment of AI at the edge. USPS entities have ideas for as many as 30 applications for ECIP. People would automatically check if a package has the right postage for its size, weight and destination, while another, which could go live this summer, would decipher damaged barcodes.
USPS also has several other IT initiatives underway to combat those concerns. For instance, they are looking into using autonomous vehicles for mail delivery and monetising their geolocation data. A February Information Technology and Innovation Foundation report touted the use of robotics for last-mile postal delivery.
Extraordinary innovation has occurred at the USPS and the work that is occurring by building an enterprisewide AI program for the USPS can be a motivator for the U.S. federal government and commercial businesses and enterprises around the globe.
According to a page, the USPS uses some of the most advanced mail processing technology in the world, including fully automated systems and robust tracking and scanning technology. These enhanced network systems enable them to provide customers with better data and better ways of using the mail. And, as the systems get smarter, the customers get smarter about the way they use the mail.
One of the many technology-enabled solutions was simplified full-service requirements for drop-shipments and customer-supplier agreements. They are giving customers better information regarding their full-service mailings, including better reports and data they collect about mailpieces and containers. They are also offering seamless entry that enables business customers to drop off their mail through streamlined, automated processes. The USPS aims to create a stronger, profitable Postal Service. And building a leaner, faster and smarter operational network is critical to achieving that goal.
AI has been utilised in many different fields for various purposes such as countering the spread of disinformation. As reported by OpenGov Asia U.S. researchers created a system that would automatically detect disinformation narratives as well as those individuals who are spreading the narratives within social media networks, called the Reconnaissance of Influence Operations (RIO) programme.
The RIO system helps determine not only whether a social media account is spreading disinformation but also how much the account causes the network as a whole to change and amplify the message. RIO classifies these accounts by looking into data related to behaviours such as whether the account interacts with foreign media and what languages it uses. This approach allows RIO to detect hostile accounts that are active in diverse campaigns.