AI-103 Certification Practice Question #53

Question

You have an application that processes scanned PDF invoices. The invoices have varied layouts and include multipage tables.
You have a pipeline that uses optical character recognition (OCR) and extracts totals and invoice numbers. The results are often incorrect because the document structure is ignored.
You need to implement a solution that provides OCR, layout analysis, and template-generalizing field extraction. The solution must NOT require training a custom model. The solution must minimize administrative effort.
What should you include in the solution?

Accepted Answer

The solution must combine OCR, layout analysis, and template-generalizing field extraction (totals, invoice numbers) across varied layouts, must NOT require training a custom model, and must minimize admin effort. Content Understanding delivers OCR, structure-aware layout analysis, and prebuilt/extraction field capabilities that generalize across invoice layouts out of the box. Azure Machine Learning (C) would mean building and training a model — directly contradicting the constraints — and Language (A) does not perform layout-aware field extraction from scanned documents. Suggested Answer and MS Learn align; 88% reflects the lack of community data plus a minor real-world overlap with Document Intelligence's prebuilt-invoice model (not offered as a choice here).

More AI-103 practice questions