Automatically
separate and group documents
Structure mixed documents and batch files to enable reliable downstream processing.
Documents are rarely structured
Documents often arrive in bundled formats. Multiple attachments in an email, batch PDFs, or scanned document stacks can contain different types of content within a single file.
It is often unclear where one document begins and another ends. Related pages cannot always be directly assigned.
Before any processing can take place, this structure must first be established.
Where processing slows down
Without a clear document structure, a manual intermediate step is required. Documents must be opened, reviewed, and split into individual components. Pages are separated and reassigned. This step is time-consuming and prone to errors. If documents are not correctly separated or grouped, this directly affects downstream processing.
The real challenge is therefore not extracting information, but preparing documents in a structured and reliable way.
Automation requires documents to be clearly separated and correctly grouped.

What does document separation and grouping mean?
Document separation and grouping describe the structured preparation of mixed document inputs. Individual documents within a file are identified, separated from each other, and related pages are correctly assigned.
The goal is a clear document structure that enables reliable downstream processing.
How does bluDELTA structure documents?
bluDELTA analyzes incoming files and automatically identifies which documents are included and how they relate to each other.
The solution detects document boundaries, separates batch files into individual documents, and assigns related pages correctly. Mixed document types within a single file are also taken into account.
This transforms an unstructured document intake into a structured foundation for further processing.
From batch documents to clear structure
Position within the overall process
Document separation and grouping are part of the first processing step within bluDELTA.
This step is handled by the Class & Split module. It ensures that documents are structured so that subsequent steps can build on them:
- Class & Split: identify, separate, and structure documents
- Extract: Retrieve information from documents
- Mapping: Assign and validate data in a business context
Without a clear document structure, these steps cannot be performed reliably.


