The challenge and the problem
In complex industries such as automotive, aerospace and mechanical engineering, the initial phase of a project often begins with the receipt of a Request for Quotation (RFQ). Historically, the analysis of these documents has been a manual, time-consuming and error-prone process. Technical requirements are usually contained in unstructured formats such as PDFs, Word documents, and Excel files, making it difficult to maintain consistency and ensure traceability of information throughout the process. The lack of automation also makes it complex to quickly and accurately enter data into business management systems.
To address these inefficiencies, MADE4.0, Solution Hub and Erre Quadro, through AI Matters have developed two interconnected projects that leverage Artificial Intelligence to automate the extraction and lifecycle management of these critical requirements.
The solution
Both projects are based on the integration of Tech Reveal technology, a Document Intelligence solution that applies advanced AI models to extract, classify, and interpret information from complex technical documents.
Thanks to AI matters, the solution will be tested in a realistic environment by optimizing the automatic extraction of technical requirements from RFQ documents, reducing analysis time and improving the quality of the information handled.
Project 1: Automated extraction and ingestion in the RM system.
The first project focuses on semantic interpretation of technical requirements contained in RFQ documents. By configuring specific machine learning models for parsing, the system can automatically identify key technical data regardless of the original file format.
- Smooth integration: Through the use of middleware and APIs, extracted data are transformed and fed directly into Requirement Management (RM) systems, specifically Jama Connect.
- Standardization: The project includes the development of a Tech Reveal module that normalizes extraction output, ensuring that data are organized according to specific business taxonomies.
Project 2: End-to-end traceability and PLM archiving.
The second project extends this automation to the entire product lifecycle, ensuring consistency and compliance. An integrated workflow was defined that tracks an RFQ from the moment it arrives to final storage in Product Lifecycle Management (PLM) systems.
- Flow orchestration: Through the use of orchestration APIs, the project ensures that every requirement is historicized and fully traceable throughout the information flow.
- Alignment: This integration ensures continuous alignment between customer requirements and product development, dramatically reducing the risk of information loss in the transition between business and engineering areas.
The Impact: Efficiency, Accuracy and Competitiveness
The implementation of these AI-based solutions, developed with the collaboration of AI-Matters, MADE4.0, Solution Hub and Erre Quadro, offers tangible competitive advantages:
- Drastic time savings: Automation significantly reduces the time required for technical analysis and response to RFQs.
- Higher quality and accuracy: Automated extraction improves the accuracy of managed requirements, leading to higher quality technical bids and reducing manual errors.
- Full visibility: Companies gain full visibility into the RFQ lifecycle, improving integration and collaboration between business and engineering departments.
- Increased competitiveness: By reducing management time and information risks, companies can handle a higher volume of requests with superior efficiency and consistency.
Through these initiatives, the transformation of unstructured data into digital and interoperable information becomes an operational reality, fostering a more agile and data-driven manufacturing ecosystem.