CCNA Implement knowledge mining and information extraction solutions Questions

Option B is correct because scanned PDFs require OCR to convert images to text. The Document Intelligence custom extraction model can process images if OCR is enabled in the skill. Option A is wrong because the issue is OCR, not the model type.

Option C is wrong because an OCR skill would duplicate functionality; Document Intelligence handles OCR internally. Option D is wrong because reindexing won't fix the missing OCR step.

Option B is correct because increasing the Azure Function timeout (in Premium or Dedicated plans) allows longer execution. Option A is wrong because the skill failure is due to timeout, not the number of skills. Option C is wrong because indexing in batches doesn't change the per-document execution time.

Option D is wrong because Document Intelligence is not used for custom Python extraction.

Option B is correct because custom Named Entity Recognition allows you to train a model to recognize custom entities like medical terms. Option A is wrong because prebuilt NER only recognizes general entities like person, location, etc. Option C is wrong because entity linking links to external knowledge bases.

Option D is wrong because PII detection is for personal information.

Azure AI Language provides key phrase extraction, entity recognition, and sentiment analysis as built-in skills. Azure AI Search provides the indexing and search capabilities. Option A is wrong because Azure AI Translator is for translation, not the required analyses.

Option B is wrong because Azure AI Document Intelligence is for extracting text from documents, not for language analysis. Option D is wrong because the custom skill would be redundant if native skills exist.

Option B is correct because custom question answering (from Azure AI Language) is designed for FAQ-like Q&A over documents. Option A is wrong because Azure AI Search alone does not provide Q&A. Option C is wrong because Document Intelligence only extracts text.

Option D is wrong because Azure OpenAI can do Q&A but requires careful grounding; custom question answering is more straightforward for this use case.

Option B is correct. The current configuration has maxFailedItems=5, meaning the indexer stops after 5 failures. Increasing maxFailedItems to a higher value (e.g., 100) allows the indexer to continue.

Option A is wrong because decreasing batch size may reduce failures but does not increase the failure tolerance. Option C is wrong because removing the schedule does not affect failure handling. Option D is wrong because increasing batch size may increase failures.

Option B is correct because Azure AI Document Intelligence (formerly Form Recognizer) is designed for extracting structured information from documents using prebuilt and custom models. Option A is incorrect because Azure AI Language is for text analytics and NLP but not optimized for scanned documents. Option C is incorrect because Azure AI Search is for indexing and searching, not extraction.

Option D is incorrect because Azure AI Vision is for image analysis, not document extraction.

Incremental enrichment requires a projection to store intermediate state and a cache key to identify documents. Option A is not required because blob metadata is not needed. Option D is not required because a custom skill is optional.

Option E is not required because incremental enrichment works without custom skills.

Option C is correct because semantic ranking improves relevance by using deep learning models to re-rank search results. Option A is incorrect because synonyms expand queries but don't necessarily improve relevance ranking. Option B is incorrect because scoring profiles are simpler and less effective for deep relevance.

Option D is incorrect because filters reduce the result set but don't improve ranking.

Option C is correct because Azure AI Search's indexer does not natively support EPUB files. A custom skill can convert EPUB to text or a supported format. Option A is wrong because the skill itself cannot handle unsupported formats.

Option B is wrong because the indexer must support the format. Option D is wrong because Document Intelligence does not support EPUB.

Option C is correct because the Read API supports multiple languages including French for OCR. Option A is wrong because the Layout model extracts tables but not necessarily text in specific languages. Option B is wrong because the custom model requires training.

Option D is wrong because the prebuilt invoice model is for invoices and may not support all languages or general text extraction.

Option C is correct because Form Recognizer (now AI Document Intelligence) can extract text, key-value pairs, and tables from documents, including handwriting. Option A is wrong because Computer Vision primarily analyzes images for objects and tags, not structured extraction. Option B is wrong because Language Service focuses on text analytics.

Option D is wrong because Speech Service handles audio.

Option D is correct because Azure AI Document Intelligence with layout model extracts text, tables, and structure from documents. Option A is incorrect because Azure AI Vision OCR extracts text but not table structure. Option B is incorrect because Azure AI Language extracts entities but not tables.

Option C is incorrect because Azure AI Search alone cannot extract content.

Option C is correct because index-level security with filters is the recommended pattern for multi-tenancy. Option A is wrong because multiple services are costly and unnecessary. Option B is wrong because data sources are not security boundaries.

Option D is wrong because skillsets are stateless and do not provide isolation.

Option D is correct because the degreeOfParallelism is set to 3, meaning three batches of 5 documents each (15 docs) are sent concurrently, exceeding the 10 docs/sec capacity. Option A is wrong because the timeout is 30 seconds, which is sufficient. Option B is wrong because context is correct.

Option C is wrong because the batch size of 5 is reasonable.

Option C is correct because it uses the appropriate skills for extraction: Document Layout skill handles tables and figures, Entity Recognition extracts drugs (as entities), Key Phrase Extraction extracts key findings, and the index includes all required fields. Option A misses Entity Recognition for drugs. Option B uses Translator unnecessarily.

Option D uses OCR skill but the Document Layout skill is more suitable for structured PDFs.

Option A (Azure AI Language) provides sentiment analysis and topic extraction. Option D (Azure AI Search with cognitive skills) can incorporate sentiment and topic extraction skills. Option B is for decision, not sentiment.

Option C is for text translation. Option E is for computer vision.

Option A is correct because the ARM template references a skillset that has not been deployed. Option B is wrong because the data source is referenced but not necessarily missing. Option C is wrong because the schedule is valid.

Option D is wrong because the field mapping is valid.

Option A is correct because you need to create a data source that points to the Blob Storage container to fetch the documents. Option B is wrong because you need a data source before creating an indexer. Option C is wrong because the indexer will create the index based on the data source.

Option D is wrong because the indexer will handle skillset execution.

Option B is correct because you need to create a custom skill in the Azure Cognitive Search skillset that calls the Azure AI Language custom entity extraction endpoint. The built-in skills do not support custom models directly. Option A is wrong because built-in skills only cover prebuilt entities.

Option C is wrong because the custom model is already deployed. Option D is wrong because a custom skill is needed before adding to the index.

Options A and C are correct. The neural model handles handwriting (A), and the table extraction capability (C) extracts tables. Option B is wrong because the prebuilt-layout model is not custom-trained.

Option D is wrong because form recognition is part of Document Intelligence but not specific to contracts. Option E is wrong because OCR is built-in and not a separate feature to enable.

Option D is correct because semantic ranking uses captions and answers; without them, it is less effective. Option A is wrong because simple scoring profiles do not use AI. Option B is wrong because more replicas improve throughput, not relevance.

Option C is wrong because increasing partition count improves indexing speed.

Azure AI Search can index metadata from Microsoft Purview using a custom indexer or data source. Option B is correct because you can create an indexer that pulls metadata from Purview's Atlas API. Option A is incorrect because Purview does not push directly.

Option C is incorrect because Power BI is for analytics. Option D is incorrect because Microsoft Foundry is a different platform.

Option B is correct because enabling semantic search improves ranking by understanding the context of multi-word queries. Option A is wrong because adding more fields does not directly improve ranking for multi-word queries. Option C is wrong because setting a higher boost on 'content' does not fix the issue of missing proximity.

Option D is wrong because changing the analyzer to a different language may not help.

Option B is correct because the prebuilt invoice model extracts tables and line items. Option A is wrong because the general document model extracts text and layout but not invoice-specific fields. Option C is wrong because the custom model requires training data.

Option D is wrong because the layout model only extracts text and tables without field mapping.

Option A is correct because Azure AI Language provides sentiment analysis and key phrase extraction as built-in skills. Option B is wrong because Document Intelligence is for document extraction. Option C is wrong because Translator is for translation.

Option D is wrong because Computer Vision is for images.

Azure AI Document Intelligence extracts text from documents. Azure AI Language provides entity recognition. A custom skill can perform redaction.

Azure AI Search indexes the content. Option A is wrong because Azure AI Translator is not needed. Option B is wrong because Azure AI Video Indexer is for video.

Option D is wrong because Azure AI Content Safety is for moderation, not redaction.

Option B is correct because Azure AI Document Intelligence has prebuilt models for handwriting and can extract fields with minimal training. Option A requires custom training and labeling. Option C uses OCR but not extraction.

Option D uses Custom Vision which is not suitable for text extraction.

Option B is correct because the prebuilt-invoice model is specifically designed to extract fields from invoices, including line items. Option A is wrong because the prebuilt-layout model extracts text and structure but not specific key-value pairs like line items. Option C is wrong because the prebuilt-receipt model is for receipts, not invoices.

Option D is wrong because the prebuilt-idDocument model is for identity documents.

Option A is correct because Azure AI Search language analyzers handle language-specific tokenization and stemming, enabling per-language search. Option B is wrong because Azure AI Translator translation of queries is unnecessary and may lose nuance. Option C is wrong because Azure AI Language's language detection is not needed if the language is known.

Option D is wrong because a single non-language analyzer (like Lucene standard) does not handle language specifics.

Option C is correct because Document Intelligence (formerly Form Recognizer) is specialized in extracting structured fields from documents. Option A is wrong because Azure AI Search is for indexing and searching, not extraction. Option B is wrong because Azure OpenAI can extract entities but is not the most cost-effective for this specific scenario.

Option D is wrong because AI Language is for text analytics but not optimized for document layout analysis.

Option C is correct because Azure AI Language provides pre-built models for key phrase extraction, entity recognition (issue/resolution), and sentiment analysis. Option A is wrong because Azure AI Speech is for speech-to-text, not text analysis. Option B is wrong because Azure AI Translator is for translation.

Option D is wrong because Azure AI Document Intelligence is for document extraction, not conversation text.

Option A is correct because using managed identity eliminates the need for keys. Option C is correct because allowing the search service's IP in the firewall ensures access. Option B is wrong because shared access keys are less secure.

Option D is wrong because disabling firewall is insecure. Option E is wrong because the search service connects to Azure Storage, not the other way.

Option A is correct because increasing the indexer execution timeout allows more time for large document extraction. Option B is wrong because enabling incremental enrichment does not affect extraction timeout. Option C is wrong because splitting PDFs into smaller files would require re-uploading.

Option D is wrong because changing the parsing mode to text does not apply to PDFs; PDFs are already parsed as text or image.

Option C is correct because Document Intelligence supports custom classification models for categorizing documents. Option A is wrong because OCR is for text extraction, not classification. Option B is wrong because layout extraction extracts text structure, not categories.

Option D is wrong because prebuilt models are for specific document types, not custom categories.

Option B is correct because enabling PII detection in the enrichment pipeline and using a custom skill to remove or mask PII fields before indexing prevents PII from being stored in the index. Option A is wrong because encryption does not prevent PII from being returned in results. Option C is wrong because field mappings control how fields are imported, not content removal.

Option D is wrong because access control restricts who can search but does not remove PII from results.

Options A and D are correct. Semantic ranking re-orders results using deep learning models to match query intent, and scoring profiles allow customizing relevance based on field weights, boosting, and freshness. Option B is incorrect because search mode 'all' returns documents containing all terms, which may not improve relevance.

Option C is incorrect because synonyms expand queries but do not re-rank. Option E is incorrect because filters narrow results but do not improve ranking.

Options A, C, and D are correct. The skill must be deployed as a web API that accepts JSON input and returns JSON output. It should handle errors gracefully.

It must be registered in the skillset. Option B is wrong because the skill should not be long-running; indexer timeouts apply. Option E is wrong because the skill can be in any language as long as it exposes a REST API.

Option C is correct because Document Intelligence's Read OCR model supports handwriting recognition; enabling it ensures handwritten text is extracted. Option A is wrong because the issue is not about custom models. Option B is wrong because the built-in OCR skill does not support handwriting.

Option D is wrong because increasing resolution doesn't enable handwriting recognition.

Custom models in Document Intelligence can be trained on a set of sample documents to learn the specific layout of a vendor's invoices, improving extraction accuracy for non-standard formats. Option A is wrong because using a prebuilt model for invoices is designed for standard layouts. Option B is wrong because Azure AI Form Recognizer (now part of Document Intelligence) supports custom models.

Option D is wrong because OCR provides text but not structured extraction.

To pass the entire document, set context to '/document' and inputs to reference '/document/content'. Option A passes only the content. Option B passes only metadata.

Option D uses wrong path separators.

Option C is correct because the suggester's sourceFields only include "content", not the "people" or "organizations" fields. Users likely want suggestions from those entity fields. Option A is wrong because the key field is required and correct.

Option B is wrong because the suggester mode is valid. Option D is wrong because the fields are correctly defined as collections.

Azure AI Document Intelligence (formerly Form Recognizer) can extract structured data from invoices, and Azure AI Vision OCR can extract text from images. Option A is incorrect because Azure AI Language doesn't process images. Option B is incorrect because Azure AI Search is for indexing, not extraction.

Option D is incorrect because Azure AI Translator is for translation.

Option B is correct because the SplitSkill splits the document into pages, and the SentimentSkill runs per page. If the split output is not properly mapped, sentiment only runs on the first page. Option A is wrong because the skill order is correct (split before sentiment).

Option C is wrong because the skill version is V3, which is valid. Option D is wrong because the context is correct.

Option A (Azure AI Vision) includes OCR and handwriting recognition. Option D (Azure AI Document Intelligence) is optimized for document extraction including handwriting. Option B is for search, not OCR.

Option C is for text analytics. Option E is for speech.

Options A, B, and D are correct. A: Create a custom classification model to differentiate document types. B: Label at least 5 samples per class to train the classifier.

D: Use the classification model as part of a composed model or in a workflow. Option C is wrong because prebuilt models are for extraction, not classification. Option E is wrong because training with only one sample is insufficient.

Option B is correct. Using Azure AI Document Intelligence's layout and OCR capabilities extracts text, tables, and handwriting. The enrichment pipeline with a custom skill using the translation service handles multilingual content, and a scoring profile with freshness boosting prioritizes recent reports.

Option A is incorrect because Azure AI Vision OCR alone does not extract table structure. Option C is incorrect because the Language service does not handle document layout. Option D is incorrect because scheduling the indexer once a week does not meet the daily update requirement.

Microsoft Syntex can use a document understanding model to classify documents and extract entities. Option A is wrong because Syntex does not use the out-of-the-box entity extraction from AI Builder directly; it uses its own models. Option B is wrong because Power Automate with AI Builder is a separate approach, not integrated with Syntex.

Option D is wrong because Azure AI Search is not needed for this scenario.

Option C is correct because Azure AI Document Intelligence's pre-built layout model can extract checkboxes, signatures, and handwritten text. Option A is wrong because Azure AI Language works with typed text. Option B is wrong because Azure AI Speech is for audio.

Option D is wrong because Azure AI Computer Vision (now part of Azure AI Vision) provides OCR but not form-specific extraction.

Option C is correct because Azure AI Search cannot index encrypted documents; the solution is to decrypt the PDF before uploading or use a decryption step. Option A is incorrect because indexers can handle large files (up to 16 MB). Option B is incorrect because unsupported file types would give a different error.

Option D is incorrect because the indexer does not need a specific parser for encrypted files.

Option B is correct because custom NER models can be called via a custom skill in the skillset. Option A is wrong because the built-in Entity Recognition skill cannot use custom models. Option C is wrong because Language Understanding is not for NER.

Option D is wrong because the indexer does not directly call external APIs; skills do.

Option A is correct because Document Layout skill handles typed and handwritten text, Entity Recognition can extract person names (parties, judge) and law-related entities, and a custom skill can parse case citations. Option B misses entity extraction for parties and judge. Option C uses OCR but Document Layout is better.

Option D uses Translator unnecessarily.

Options A, C, and E are correct. A: Skillset execution time must be within indexer timeout limits. C: Azure Functions can scale to handle concurrent requests.

E: Incremental enrichment reduces reprocessing. Option B is wrong because knowledge stores are for structured output, not performance. Option D is wrong because semantic ranking is for search relevance, not extraction.

Option D is correct because Document Intelligence's custom model can be trained on handwritten forms, and Language Service can be used to post-process entities. However, the best approach is to use Document Intelligence with a custom model trained on handwriting. Option A is wrong because Computer Vision OCR does not handle handwriting well.

Option B is wrong because Language Service alone cannot extract from images. Option C is wrong because Form Recognizer (Document Intelligence) prebuilt models are not optimized for handwriting.

B and D are correct. B: The OCR skill in Azure AI Search uses Azure AI Vision. D: Azure AI Document Intelligence uses OCR.

A is for translation; C is for speech; E is for conversational AI.

Option A is correct because the Text Analytics for Health model is a pre-built model for extracting healthcare entities. Option C is correct because Azure AI Search is used to index the extracted data. Option D is correct because the Text Analytics for Health skill in Azure AI Search applies the model.

Options B and E are incorrect: Language Understanding is for conversational AI, and Form Recognizer is for form data.

Option A is correct because a custom synonym map can define equivalent terms like 'disk' and 'hard drive'. Option B is wrong because semantic ranking re-ranks results but does not add synonyms. Option C is wrong because scoring profiles boost by fields, not synonyms.

Option D is wrong because filters reduce results but do not expand queries.

Azure AI Document Intelligence (formerly Form Recognizer) is designed to extract key-value pairs from forms. Option B is incorrect because Vision is for OCR, not structure. Option C is incorrect because Language is for text analysis.

Option D is incorrect because Search is for indexing.

Option D is correct because one skillset can handle all document types (using Document Layout skill), translate Spanish to English, extract sentiment from reviews, and extract key phrases for features. Document Intelligence is not needed for reviews. Option A misses sentiment analysis.

Option B uses two pipelines unnecessarily. Option C misses translation.

Option B is correct because if the indexer fails, documents are not indexed. Option A is wrong because throttling would affect all documents, not a subset. Option C is wrong because the search service would report failures for other reasons.

Option D is wrong because missing semantic configuration affects ranking, not indexing.