AI-900 Question 28
Single answerA company wants to build a system that can automatically extract information from thousands of scanned legal documents, such as client names, contract dates, and clauses, to make the data searchable and accessible for their legal team. Which Azure service-based workload would be most appropriate for this scenario?
- A
Natural language processing for sentiment analysis
- B
Knowledge mining using Azure Cognitive Search
- C
Computer vision for object detection
- D
Machine learning for predictive analytics
Show answer and explanation
Correct answer: B
Explanation
Knowledge mining workloads, powered by Azure Cognitive Search, are designed to extract insights from large volumes of unstructured or semi-structured data. In this scenario, Azure Cognitive Search can process scanned legal documents, extract relevant information like client names and contract dates, and make this data searchable for the legal team. This makes it the most appropriate workload for the use case.
- A. Incorrect.
Natural language processing for sentiment analysis is focused on understanding the sentiment behind text, such as identifying whether a review is positive or negative. It is not suitable for extracting structured information from documents.
- B. Correct.
Knowledge mining using Azure Cognitive Search is the correct choice as it enables extracting, enriching, and searching information from large volumes of unstructured and structured data, such as scanned legal documents.
- C. Incorrect.
Computer vision for object detection is used for identifying and classifying objects in images or videos. It does not handle extracting information from text-based documents.
- D. Incorrect.
Machine learning for predictive analytics is used for identifying patterns and making predictions based on data. It is not specifically designed for extracting information or making documents searchable.