Продакшен-архитектура автоматической записи по звонку
Продакшен-архитектура автоматической записи по звонку
Ответить самому
Сначала сформулируйте ответ как на собеседовании, затем откройте разбор и оцените себя.
Короткий ответ
Put completed calls into a queue, process audio once, pass lightweight artifacts between services, validate extracted bookings, then write with idempotency and transactional slot reservation.
Полный разбор
After a call ends, store the audio in object storage and send a job id to a queue. Workers run VAD, ASR, extraction and validation. Avoid moving large audio through many services; pass references, transcripts and JSON artifacts instead.
Before writing a booking, validate that the branch exists, the slot is open, the confidence is high and the customer accepted. The write path should be idempotent by call id, and slot reservation should be transactional or protected by a uniqueness constraint on branch and time slot.
If the model is slower than the operator workflow, design the product flow carefully. Either the operator books during the call and the model audits/fills missing fields, or the model writes only when there is no conflict. Add human review for conflicts, low confidence and changed slots.
Теория
ML output becomes a product action only after validation, idempotency and conflict handling are designed.
Типичные ошибки
- Let the model write directly to the calendar with no validation.
- Pass large audio blobs through every service.
- Ignore double-booking and idempotency.
- Assume slow asynchronous extraction cannot affect operations.
Как отвечать на собеседовании
- Mention queue plus object storage reference.
- Use a transactional slot-reservation rule for double-booking.