AZ-900 Describe Azure architecture and services Practice Question

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Azure Computer Vision OCR

  Why it's wrong here

  Azure Computer Vision OCR (Read API) detects and extracts printed and handwritten text from images and PDFs, returning each word and line with bounding box coordinates. However, OCR alone is agnostic to document semantics — it cannot understand which extracted text corresponds to specific form fields or table cells; Form Recognizer adds this layout and schema understanding on top of OCR.

• ✓

  Azure Form Recognizer

  Why this is correct

  Azure Form Recognizer (also known as Azure AI Document Intelligence) is the correct service because it uses machine learning models to extract text, key-value pairs, selection marks, and tables from forms and documents. It offers prebuilt models for invoices, receipts, and IDs, plus the ability to train custom models on domain-specific forms, making it purpose-built for turning unstructured or semi-structured documents into structured JSON output.

• ✗

  Azure Text Analytics

  Why it's wrong here

  Azure Text Analytics (part of Azure AI Language) performs natural language processing tasks such as sentiment analysis, key phrase extraction, and named entity recognition (NER) on raw text. It does not process scanned document layouts, nor does it return key-value pairs and table structures from forms; its input is text, not document images or form files.

• ✗

  Azure Cognitive Search

  Why it's wrong here

  Azure Cognitive Search is a cloud search-as-a-service solution that indexes content from data sources and exposes them through a query API. Although it can be combined with an AI enrichment pipeline (including Form Recognizer) to add extracted fields, its purpose is storage, indexing, and retrieval of documents — not the direct extraction of structured form data as a standalone service.