A university admissions office wants to use a service that can accept a photo of a handwritten application form and output the applicant's name, address, and date of birth as structured text fields, without training a custom model. Which Azure AI capability should the office use?
Select an answer to reveal the explanation.
Short Explanation
You need structured fields from a photographed handwritten form, not just a blob of text. Azure AI Document Intelligence is built to read forms and hand back labeled fields like name, address, and date of birth without custom training.
Full Explanation
Azure AI Document Intelligence for extracting structured fields from forms is the right choice because it is purpose-built to take images or scans of forms, including handwritten ones, and return structured key-value fields such as name, address, and date of birth, which is exactly what the admissions office needs without building or training a custom model from scratch. Computer vision optical character recognition (OCR) for extracting printed text only is incorrect because basic OCR only returns raw extracted text without organizing it into named fields, so the office would still have to parse the output manually. The knowledge mining pipeline that indexes existing digital documents is incorrect because knowledge mining is designed to index and make searchable a large existing collection of documents, not to extract structured data from a single incoming form. The conversational language understanding model to interpret spoken input is incorrect because conversational language understanding processes spoken or typed natural language utterances to determine intent, which has no relevance to reading handwriting from an image.