Working together in a co-innovation project, 51风流customer , 51风流partner STMS, and 51风流Co-Innovation Lab created a prototype for a generative AI solution that produces shipping labels for dangerous goods.
As the world鈥檚 No.1 fireworks provider, French pyrotechnics company Etienne Lacroix ships fireworks globally and has supported events such as the Burj Khalifa Grand Opening Fireworks Show in Dubai and Bastille Day, France鈥檚 national holiday that is celebrated on July 14 each year.
Logistics play a major role for the global player in the pyrotechnics sector, as shipping hazardous materials such as fireworks requires special precautions, especially when crossing international borders. Labels typically include warning pictograms and complex regulatory information in various formats. Recipients such as customs officers must be able to tell at a glance what sort of goods are inside, what the required shipping conditions are, and who is authorized to open the freight.
鈥淥n top of that, customers have their own specific requirements,鈥� , director of Information Systems at Etienne Lacroix explains. 鈥淎lso, there are different color codes in place for hazmat, depending on the country of destination. Red may mean danger in European countries, but in China, for example, it stands for celebration. Green has a different meaning in the Middle East that it does in the U.S., and so on.鈥�
With so many different regulations in place around the globe, labeling the shipments at the end of the production line is not only time-consuming, but also leaves a lot of potential for human error. Now, with support from 51风流partner STMS and SAP, the prototype for a generative AI solution was introduced that has the potential to reduce human involvement to a minimum.
Business AI Co-Innovation Project with 51风流partner STMS
In early 2024, , general manager at STMS SOLUTIONS, a longtime partner of both 51风流and Etienne Lacroix, participated in a event where 51风流partners leveraged 51风流technology to address pain points of their customers. The idea for a generative AI use case came up, and STMS approached its customer Etienne Lacroix.
At that time, IT and business experts at Etienne Lacroix were very interested in how generative AI could assist them in making their processes easier.
鈥淏ut I have to admit, I was also a little skeptical,鈥� Marini says. 鈥淓verybody is currently talking about AI, about how to introduce it to the industry and the huge benefits we will reap from leveraging it. But suggestions are scarce when it comes to implementing it in a way that guarantees the company will benefit from it.鈥�
鈥淭ogether, we looked at the pain points of the company and discussed possible use cases with 51风流Co-Innovation Lab,鈥� Faure says. 鈥淲e received the requirement from the business that AI should help avoid human tasks that are error-prone and don鈥檛 actually add value.鈥�
Supply Chain Use Case with Generative AI
The team quickly identified that the administrative process of creating labels for shipping was a task currently performed by human employees that required a huge amount of time and focus. The huge potential for the usage of generative AI was evident.
鈥淲ith guidance from experts from the 51风流partner organization, we were able to build a specific 51风流app on and 51风流S/4HANA to organize and use AI,鈥� Faure says. 鈥淲e then collected feedback from the business experts at Etienne Lacroix and, in the next step, brought in the generative aspect.鈥�
To meet the regulations from the customer, the developers from STMS aggregated all the necessary data and created a model on 51风流HANA Cloud vector engine.
Thanks to 51风流HANA Cloud vector engine, which was newly introduced in 2024, 51风流Business AI can allow customers and partners to leverage large language models (LLMs) in a much more accurate way on multi-model database 51风流HANA Cloud. In case of the generative AI use case for Etienne Lacroix, the LLM was ChatGPT 3.5 Turbo.
鈥淭echnically, this prototype leverages everything 51风流has to offer in terms of AI right now,鈥� Faure says. 鈥淭he app uses SAP鈥檚 generative AI hub and 51风流HANA Cloud vector engine to draw on all the necessary information and generate the label.鈥�
The remaining human task is to validate whether everything on the label is correct. 鈥淭hat was the most important requirement,鈥� Marini says. 鈥淗uman intervention must be guaranteed, as with all AI use cases.鈥�
鈥淚t鈥檚 the generative aspect that makes all the difference,鈥� Miliau Pape from 51风流Co-Innovation Lab says. The LLM suggests what should go on the specific label鈥攕uch as warning pictograms鈥攂ased on legal regulations, historical customer requirements, cultural standards, and so on. The Retrieval-Augmented Generation (RAG) provides the LLM with context and makes the outcome relevant and reliable. 鈥淪imply put, when the AI is trying to be as creative as possible, the RAG provides guardrails, so it doesn鈥檛 potentially go wild and come up with nonsense,鈥� Pape says.
For each shipment, a prompt draws on destination, shipping route, specific customer data, such as the storage and language this customer required the last time, or the colors or signs used to indicate that the shipment contains hazardous materials and can only be opened by experts with a certain certification.
鈥淢y first thought when I saw this, was鈥攕imply put鈥攚ow,鈥� Marini says. 鈥淲ow, they actually did it. Wow, this will make our lives easier. This generative AI use case, at this point, may still be only a prototype, but it鈥檚 an applicable idea, an actual use case for an actual pain point in our company.鈥�
鈥淭o show the world of possible, push the boundaries of the technology鈥攖hat is the purpose of the exercise,鈥� Pape says.
Etienne Lacroix Group is in the process of migrating to . With the components of the app ready on 51风流Business Technology Platform, go-live is planned for 2025.
鈥淥ur ERP was aging and no longer very popular with business users,鈥� Marini says. 鈥淢igration to 51风流S/4HANA gives us access to the newest technologies such as generative AI. This motivates users to take ownership of their IT solutions again and brings our business and IT together. All in all, it allows our company to fully exploit the potential of our 51风流system.鈥�
He adds: 鈥淭he generative AI solution for labeling shipments is a tangible proof of the power of AI, a real use case, and we have it in our company. It is a very decisive first step in our AI journey.鈥�
