Ki-based Further Development of the Digitization of the Profession Archive Tender

Procurement Summary

Country : Germany

Summary : Ki-based Further Development of the Digitization of the Profession Archive

Deadline : 22 Apr 2024

Other Information

Notice Type : Tender

TOT Ref.No.: 99199899

Document Ref. No. : 2024-03-21 Digitalisierung des Berufe-Archivs

Competition : ICB

Financier : Self Financed

Purchaser Ownership : Public

Tender Value : Refer Document

Purchaser's Detail

Purchaser : FEDERAL INSTITUTE FOR VOCATIONAL TRAINING
Federal Institute for Vocational Training
Street, house number: Friedrich-Ebert- Allee 114-116
Postcode (postcode): 53113
Location: Bonn
Germany
Email :vergabe@bibb.de

Tender Details

Processing of scanned documents, as a single PDF or in the form of several image files or PDFs in alphabetical order.

- Preprocessing, d. H. Correction of brightness and contrast, straightening of the pages etc.

- Execution of text recognition (OCR) with suitable methods and models.

- Extraction of structural elements, i.e. lists, footnotes, headings and in particular from tables.

- Extraction of meta information, i.e. the date of the document, page information, etc.

- Automatic detection of the profession or further training profession and annotation of an URI or ID of the GLMO.

- Automated annotation of the text type, e.g. training regulations, job profile, ...

- Save the data as a TEI-XML and in a suitable database in the Bibb research network.

- Transfer to a single document (PDF), embedding text (whereby the Tei-XML document or the database is considered a reference).

- The web application must be able to compensate for existing data in the database with the new documents and thus link various documents to a data record.

- Different user groups have writing and reading-, ...
Procedure type: National public tender

Documents

 Tender Notice