AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Your organization is using Azure AI Document Intelligence to process a mix of invoices and purchase orders. You need to ensure that documents are correctly classified before extraction. Which THREE steps should you take?
⚠ Common exam trap
Watch out — candidates often confuse prebuilt models (which perform extraction) with classification capabilities, assuming they can automatically identify document types without a dedicated classifier.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Create a custom classification model in Document Intelligence
Option B is correct because a custom classification model in Azure AI Document Intelligence is the required resource for identifying document type before extraction, since prebuilt models extract fields but do not perform custom document classification. Option C is correct because training a custom classification model requires a minimum of 5 labeled samples per document type, which provides the model with enough examples to distinguish invoices from purchase orders. Option D is correct because after classification, you must chain the classification model with the appropriate extraction models so each document is routed to the correct extraction model for field retrieval. Option A is incorrect because one sample per type is insufficient; the minimum is 5 labeled samples per document type. Option E is incorrect because prebuilt invoice and purchase order models are extraction models, not classification models, and they do not classify documents before extraction.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Train the classification model with one sample per type
Why it's wrong here
A custom classification model needs several samples per document type to learn distinguishing features; one sample per type cannot generalise and will misclassify. One sample is tempting when labelled data is scarce, but custom neural classification is the right approach only with a representative, adequately sized training set.
- ✓
Create a custom classification model in Document Intelligence
Why this is correct
A custom classification model in Document Intelligence identifies each document's type before extraction, letting the pipeline route invoices and purchase orders to the appropriate extraction model. This directly satisfies the requirement to classify correctly beforehand.
- ✓
Label at least 5 samples for each document type
Why this is correct
Labelling at least five samples per document type supplies the minimum training data a custom classification model needs to distinguish invoices from purchase orders. This satisfies the stem's requirement to classify documents correctly before extraction, since the model learns each class's layout and content patterns from those labelled examples.
- ✓
Chain the classification model with extraction models
Why this is correct
Chaining routes each document through the custom classifier first, then dispatches it to the matching extraction model (invoice or purchase order). This satisfies the requirement that documents are correctly classified before extraction, preventing mismatched field extraction across the mixed document types.
- ✗
Use the prebuilt invoice and purchase order models for classification
Why it's wrong here
Prebuilt invoice and purchase order models extract fields from documents already known to be those types; they do not classify an unlabelled mix. They are tempting because they are the obvious extraction choice, and they would be correct once classification has routed each document to the right extractor.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.