BLACK FOREST HACKATHON

🚀 AI-driven Supplier Certificate Validation and Compliance Analysis for Enhanced QC

🔍 Problem Statement: Validating and analyzing supplier conformity certificates is a slow, manual process that relies heavily on human resources and is prone to errors. This inefficiency impacts compliance, process robustness, and
strategic decision-making. Automating certificate validation with AI could enhance security, streamline workflows, and unlock valuable insights.

🎯 HACKATHON CHALLENGE: How might we develop an AI-driven solution that extracts and validates numerical data from supplier certificates using OCR technology? The system should compare extracted values against predefined
compliance requirements, flag discrepancies automatically, and store all data in a centralized database for trend analysis and predictive insights.

📊 Available Data & Resources: The solution will leverage existing supplier certificates in PDF format, a structured database of compliance requirements, and annotated datasets for AI training. OCR technology will extract relevant information, while a secure database infrastructure will store validation history, enabling further analysis and continuous
improvement.

🏆 Success Criteria: Success will be measured by the accuracy of data extraction, reduction in manual validation time, scalability to handle growing document volumes, and the system’s ability to improve process robustness and compliance efficiency.

💡 Key Considerations: Key considerations include ensuring adaptability to various certificate formats, compliance with data privacy regulations.

🚀 Service Specification Document Transformer

🔍 Problem Statement: Processing complex PDFs like service specification documents (Leistungsverzeichnis) to extract actionable business insights is both time-consuming and error-prone. This often delays the conversion of service
listings into offers that can be seamlessly imported into ERP systems.

🎯 HACKATHON CHALLENGE: How might we use AI and advanced document processing to develop an interface where users can upload a Service Specification Document (of varying structure), automatically extract and classify
into products and services, and reformat them into editable Quotation Items that can be exported as XML for ERP integration?

📊 Available Data & Resources: Participants will have access to: Sample Service Specification Document PDFs, Our company’s product and service catalogs, Quotation Item Type (Class) to Article Number Mapping, Guidelines on the expected output format for ERP integration.

🏆 Success Criteria: A successful solution will accurately extract and highlight relevant sections from the PDF with at least 80% accuracy, classify Quotation Items as “product” or “service” with the same level of precision, enable users to
select, deselect, and edit extracted items, and export a clean, structured XML file ready for ERP import.

💡 Key Considerations: Focus on accuracy and ease of use for non-technical users. Clear user feedback during the extraction and editing process will be critical.

🚀 Human interaction interface for mobile robots in a manufacturing environment

🔍 Problem Statement: In today’s manufacturing landscape, having mobile robots around you is turning into a commodity. But currently, these robots are subject to a centralized control and therefore lack of flexibility in situations that would require the robot to adjust its protocol. This issue leads to inefficiency due to cumbersome and complex process adoptions.

🎯 HACKATHON CHALLENGE: How might we interact with mobile robots such that the interplay between workers and robots becomes more natural; leading to a higher robustness and a better experience?

📊 Available Data & Resources: Participants will have access to a mobile robot. The robot is able to navigate to coordinates, has a standardized ROS2 and a simple REST API, has onboard sensors available: RGB camera, laser scanner (accessible via ROS2) or can integrate sensors of your own notebook.

🏆 Success Criteria: A successful solution should have an intuitive user interface and be presented in a live demo. Graphical interfaces are accepted in the same way as gesture control, voice control, or similar.

💡 Key Considerations: Solutions should be user-friendly, reflect realistic scenarios, work in real-time, integrate with existing systems. Should run on the notebook.

🚀 Optimizing Small-Scale Storage and Plug-In Solar for Grid Stability and Cost Savings

🔍 Problem Statement: Small-scale battery storage for plug-in solar systems is not optimized for grid demand. Users charge batteries based on electricity prices rather than grid conditions, possibly overloading the grid at peak solar production times while missing opportunities to use excess renewable energy. There are no dynamic incentives for prosumers to adjust their energy use, leading to inefficiencies in balancing supply and demand.

🎯 HACKATHON CHALLENGE: How might we develop an innovative solution that helps prosumers (users with solar and storage) optimize their energy consumption and feed-in behavior to support grid stability, reduce CO₂ emissions, and maximize financial benefits?

📊 Available Data & Resources: Real-time electricity prices & grid demand APIs, Weather forecasts for solar power predictions, Battery & inverter data for energy flow insights, Smart home hardware (sockets, sensors, tablets, etc.) for prototyping

🏆 Success Criteria: A successful solution should balance the grid by optimizing consumption and feed-in based on demand, reduce CO₂ impact by using green electricity efficiently, maximize financial benefits for prosumers and be simple, user-friendly, low-cost, open-source, and scalable.

💡 Key Considerations: The solution should prioritize simplicity, low costs, ease of implementation,
open-source accessibility, and clear documentation to ensure widespread adoption and usability.

coming soon