Success story: With AI efficiency to green steel
The steel manufacturer GMH Group processes plant certificates and other documents with the help of AI. With cbs AID (Advanced Integration of Documents), data is extracted with an accuracy of 99.79 percent and transferred to SAP. This increases the level of automation and process reliability at GMH, while the replacement of outdated OCR solutions creates cost benefits. The efficiency and effectiveness potential that has been harnessed is supporting the GMH Group in its transformation to green steel. Extracting information from documents and entering it into an SAP system: This error-prone process leads to delays and prevents employees from carrying out higher-value activities.
The challenge of recycling
The GMH Group has set itself the goal of comprehensively reducing the effort involved in document processing and relieving the burden on employees. Starting with works certificates, the steel producer has created a powerful AI backbone that is being expanded to include other document types. With the G.A.D.G.E.T. project, GMH has turned a compliance bottleneck into a strategic advantage. The fact that GMH started with mill certificates was no coincidence. In steel production, every delivery of primary material is accompanied by such a document. These are inspection and acceptance certificates that are essential for SAP-based production planning. They contain quality and compliance-relevant information such as batch, order number and chemical composition. As a pioneer in CO2-low steel production, GMH-Gruppe uses almost all of its
100 percent recycled material. This presents challenges: the number of suppliers and their deliveries is very large, which means that a large number of works certificates have to be recorded and transferred to the SAP system. Roman Michel, Senior Consultant SAP MM at GMH Systems, explains: „Factory certificates are extremely complex. Due to their high volume and their importance for our production processes, we needed a solution that processes these factory certificates both error-free and with as little effort as possible.“
Standardized process for all
Until now, conventional OCR solutions (Optical Character Recognition) were used. These used templates for recognition and did not meet the requirements in terms of flexibility and cost efficiency. The structure of plant certificates changes frequently, which made it necessary to adapt the software just as frequently and expensively. Individual plants also extracted the information completely manually, which was time-consuming and error-prone.
The GMH Group decided to consistently digitize these factory certificates with a uniform, modern AI solution. The choice fell on cbs AID - Advanced Integration of Documents. „There was a need for a modern and easy-to-maintain solution that would ensure a standardized process for all suppliers with a high level of accuracy. This is exactly where cbs AID proved to be the optimal choice,“ says Roman Michel. In addition, cbs helped design the architecture and implementation.
GMH Group
The GMH Group is a leading German steel producer and processor based in Georgsmarienhütte, Lower Saxony. The group of companies comprises more than 15 medium-sized production companies with around 6000 employees. As a pioneer in the production of green steel, GMH Group uses state-of-the-art electric arc furnaces in its production, which emit 80 percent less CO2-emissions than conventional production processes. Almost exclusively recycled material is processed. The GMH Group generates an annual turnover of around two billion euros. Its customers worldwide include companies from the automotive industry, mechanical and plant engineering, railroad technology, energy generation, transport logistics, aerospace, agriculture and construction machinery. GMH has set itself the goal of being completely climate-neutral by 2039.
Automation through AI
cbs AID uses Agentic AI and requires no templates or vendor-specific training. The SAP BTP-based solution first captures all available information from the document and then performs a contextual analysis to identify and extract the relevant data. Thanks to the integration via the SAP BTP
into the backend ERP system, the data is verified, including a warning system for end users in the event of deviations. After a final human check via a dashboard, the data is automatically transferred to the SAP system. As custom AI, cbs AID is adapted to the customer's individual requirements and therefore significantly outperforms standard AI solutions in terms of accuracy and flexibility. With SAP BTP as a layer, the AI services are cleanly decoupled from the SAP core and yet deeply integrated into the processes.
After the proof of concept, GMH Group initially introduced cbs AID in the pilot plants and achieved a near-perfect extraction accuracy of 99.79%. „That is an outstanding value. The solution clearly outperforms conventional extraction methods in terms of quality and speed. We save costs, minimize errors in the process, increase data quality and operational efficiency,“ explains Roman Michel. The solution works - and the impact is measurable.
Since cbs AID also reliably recognizes changing formats and new suppliers without having to be retrained, maintenance costs are reduced by 95 percent. No effort is required for the onboarding of new suppliers or layouts. As a result, a positive return on investment of 230 percent is achieved within a period of three years. The solution is now being rolled out continuously in other plants.
Other document types
The cbs AID framework is flexible, scalable and easy to expand with additional document types, from invoices to complex forms. Based on the experience gained, the GMH Group is currently rapidly expanding the use of cbs AID to include delivery bills and order confirmations.
„Our aim is to be innovative not only in the field of green steel, but also in the use of AI. Accordingly, we are driving forward further use cases,” emphasizes Roman Michel. To this end, an AI backbone has been created that strengthens GMH Group's green steel strategy and its position as an industry innovator through smarter, more reliable and faster processes.
cbs AID: GenAI and OCR
Advanced Integration of Documents - uses generative AI to efficiently process unstructured, visually readable documents.
cbs AID does not use templates or supplier-specific training. It is customized to the customer's specific requirements. By combining OCR and Large Language Models (LLMs), the system improves the content capture and processing of documents. The implementation of the solution for the Certificate of Origin procedure has an impact in these areas:
- Efficiency: By automating document capture and approval, the solution shortens processing times, enables faster processing and minimizes bottlenecks in the workflow.
- Accuracy: The AI-driven data extraction feature accurately captures key information from supplier declarations, eliminating the need for manual data entry and reducing the risk of errors that can lead to compliance issues.
- Collaboration: The platform enables suppliers to get directly involved in the CoO process, shifting some of the workload from internal teams to suppliers. This promotes better collaboration and communication and streamlines the entire process.
- Visibility: Real-time tracking capabilities give organizations a comprehensive view of their document flow, allowing for proactive management and quick resolution of issues.
- Cost reduction: By reducing manual labor and improving operational efficiency, cbs AID contributes to cost savings, allowing companies to use their resources more effectively.
- Compliance: The solution ensures compliance with evolving international trade regulations, reduces the risk of penalties and promotes regulatory confidence.
To the partner entry:
DE 
EN 
ES 
FR 
