AI-102 Question 392
Single answerA company needs to process thousands of scanned invoices daily to extract key information such as invoice numbers, dates, and total amounts. They want to implement an Azure AI Document Intelligence solution that ensures high accuracy and requires minimal manual configuration. Which approach should they take?
- A
Use the prebuilt 'Invoice' model in Azure AI Document Intelligence
- B
Train a custom model using labeled data to extract invoice fields
- C
Use Azure Cognitive Search with Optical Character Recognition (OCR) skill
- D
Manually design a template for each invoice format and use Azure Logic Apps for processing
Show answer and explanation
Correct answer: A
Explanation
The prebuilt 'Invoice' model in Azure AI Document Intelligence is a pre-trained, ready-to-use solution that extracts key fields from invoices with high accuracy, requiring minimal configuration. This makes it the most efficient and effective approach for processing large numbers of invoices daily.
- A. Correct.
The prebuilt 'Invoice' model in Azure AI Document Intelligence is specifically designed to extract common fields from invoices with high accuracy and minimal configuration, making it the ideal solution for this scenario.
- B. Incorrect.
While training a custom model can achieve accurate results for invoice processing, it requires labeled data and significant effort to prepare and train the model. This approach is unnecessary since a prebuilt model is already available for invoices.
- C. Incorrect.
Azure Cognitive Search with OCR can extract text but lacks the domain-specific capabilities to identify and structure key invoice fields like invoice numbers, dates, and amounts. It is not the best fit for this task.
- D. Incorrect.
Manually designing templates for each invoice format is a tedious and error-prone process. Azure AI Document Intelligence eliminates the need for such manual efforts with its prebuilt models.