Microsoft Certified: Azure AI Engineer AssociateImplement natural language processing solutionsMedium
A financial institution is developing a compliance monitoring system that needs to automatically scan large volumes of customer communications (emails, chat transcripts) to identify and redact sensitive personal information, such as credit card numbers, social security numbers, and bank account details, before archiving. Which Azure AI Language feature should be used?
- ACustom Text Classification
- BPII Detection
- CNamed Entity Recognition (NER)
- DKey Phrase Extraction
Show answer & explanationAnswer & explanation
Correct answer: B. PII Detection
PII Detection (Personally Identifiable Information Detection) is a specialized feature within Azure AI Language designed specifically to identify and redact sensitive personal information like credit card numbers, social security numbers, and other privacy-sensitive data. NER is more general for named entities, and Key Phrase Extraction/Custom Text Classification serve different purposes.
Why the other options are wrong
- A. Custom Text Classification categorizes entire documents, not extracts or redacts specific sensitive data points.
- C. NER identifies named entities like people or organizations, but PII Detection is specialized for sensitive personal information types.
- D. Key Phrase Extraction identifies general important concepts, not specific sensitive personal data.
PII Detection (Azure AI Language)
A feature of Azure AI Language that automatically identifies, categorizes, and can redact sensitive personal information (PII) from unstructured text.
- Detects various types of PII (e.g., credit card numbers, SSN, phone numbers).
- Can be used for compliance, privacy, and data anonymization.
- Supports multiple languages.
Memory trick: To protect personal info, you need PII Detection, not just general entity spotting.