A bookkeeping service receives thousands of standard vendor invoices each month and needs the vendor name, total amount, and invoice date extracted. The team has no labeled samples and wants to start immediately. Which Document Intelligence option is most appropriate?
Show answer and explanation
Answer: A
The prebuilt invoice model is trained to extract common invoice fields, including vendor name, totals, and dates, without requiring you to label training documents. Because these invoices follow standard layouts, the prebuilt option meets the need immediately. A custom classification model sorts documents into categories, a synonym map affects search terms, and a knowledge store saves enrichment output, so none of them extract those fields.
Why the other options are wrong
- B. A custom classification model assigns documents to categories after training on labeled examples. It does not extract vendor totals and dates, and it requires labeled data the team lacks.
- C. A synonym map broadens or links search terms in a query. It cannot read invoices or pull fields out of document images.
- D. A knowledge store saves enriched output from a skillset into storage. It records extraction results but does not perform the field extraction itself.