Free Microsoft Azure AI-102 Actual Exam Questions - Question 7 Discussion
document processing requirements and the technical requirements.
You upload the receipt images to the From Recognizer API for analysis, and the API returns the
following JSON.
Which expression should you use to trigger a manual review of the extracted information by a
member of the Consultant-Bookkeeper group?
Maybe B is better since it checks confidence across all fields, not just MerchantName.
B imo, it covers any field under 0.7, safer for catching issues than just MerchantName.
Maybe B works better since it checks if any field has confidence below 0.7, which is a broader way to catch uncertain data needing review. D only focuses on MerchantName, which might miss other critical low-confidence fields.
Good point—MerchantName is crucial; D makes sense for manual review. D
Maybe D works best here since the question is about triggering manual review, and MerchantName is a key field for receipts. If the JSON only has confidence for MerchantName, B wouldn't apply properly because it checks all fields. Also, A just checks docType, which doesn't tie to confidence levels. C checks for confidence above 0.7, which is the opposite of what you want for flagging uncertain data. So focusing on MerchantName confidence under 0.7 seems the most targeted and practical approach for manual review.
If only MerchantName has confidence info, D fits better than B here.
B/D? I’m ruling out A since docType check doesn’t relate to confidence for manual review. C’s out because it checks confidence above 0.7, which isn’t what you want to flag. Between B and D, B looks at any field’s confidence below 0.7, so it’s broader, but if the JSON only shows confidence for MerchantName, then D is more precise. If the JSON includes confidence for multiple fields, B makes more sense; otherwise, D is safer to catch low-confidence on a key field.
Not C, the question doesn’t specify which field confidence to check. Shouldn't we trigger manual review if any key field like MerchantName has low confidence, like option D suggests?