Extract Information with Azure Content Understanding in Foundry Tools AI-102 Practice Questions (Page 6)

Questions 26–30

1. 26foundation · easy

   Which Azure Content Understanding feature is best suited for extracting the 'invoice total' from a set of invoices?

   • AContent processing
   • BDocument classification
   • CImage extraction
   • DAttribute detection
   Reveal Solution Discussion Select an answer first
2. 27application · medium

   A research firm collects long-form interview transcripts in text files and audio recordings. They need to generate a concise summary of each interview and extract the interviewee's name and the interview date. Using Azure Content Understanding in Foundry Tools, what should they build?

   • AA document classification pipeline that categorizes the interview type and extracts the name.
   • BA table extraction pipeline to pull the name and date from any tables in the transcript.
   • CA custom pipeline that accepts text and audio, with summarization and entity extraction for name and date.
   • DAn OCR pipeline to read the text files and then manually summarize and extract fields.
   Reveal Solution Discussion Select an answer first
4. 28application · medium

   A customer support center receives a mix of emails with attached images, PDFs, and audio voicemails. They want to process all these formats to extract text from images and documents, and generate a summary of each customer issue. Using Azure Content Understanding in Foundry Tools, what should they build?

   • ASeparate pipelines for each content type, each with OCR and summarization.
   • BAn OCR pipeline for images and PDFs, and a separate audio transcription pipeline with summarization.
   • CA document classification pipeline that categorizes the content type and then processes it manually.
   • DA single custom pipeline that accepts images, PDFs, and audio, with OCR for text and summarization for the issue.
   Reveal Solution Discussion Select an answer first
5. 29application · medium

   A healthcare provider receives scanned insurance claim forms that contain handwritten patient information, a printed table of procedure codes, and a signature block. They need to extract the patient name, the procedure codes from the table, and the date of service into structured JSON. The forms vary in layout but the fields are always in the same relative positions. What should they configure in Azure Content Understanding in Foundry Tools?

   • AEnable image extraction to pull the signature block as an image and then use OCR on that image to infer the patient name and procedure codes.
   • BCreate a custom field extraction pipeline with OCR enabled, define fields for patient name, date, and a table field for procedure codes, then test and publish the pipeline.
   • CConfigure a document classification pipeline to categorize the form as a claim and rely on the category label to provide the patient name and procedure codes.
   • DUse the built-in document summarization pipeline to generate a summary of the claim form and then manually copy the patient name and procedure codes from the summary.
   Reveal Solution Discussion Select an answer first
6. 30foundation · easy

   What is the main goal of document summarization in Azure Content Understanding?

   • ATo extract tables and structured data
   • BTo extract key points and essential information from a document
   • CTo identify the document's category
   • DTo extract images embedded in the document
   Reveal Solution Discussion Select an answer first