Smart reply for UberChat

概要

Uberの運転手向けに顧客に対して1クリックで返信できるsmart replyを提供した

language detection, tokenizationの後Doc2Vecでmessageをembedding、その後intentを分類し、intentに応じた返答を探す

1. Sender side (rider app) sends a message.

2. Once our back-end service receives the message, it sends it to the machine learning service in Michelangelo.

3. The machine learning model preprocesses and encodes the message, generates prediction scores for each possible intent, and sends them back to the back-end service.

4. Once the backend service receives the predictions, it follows reply retrieval policy to find the best replies (in this case, the top four).

5. Receiver side (driver-partner app) receives the suggestion and renders them on the app for the driver-partner to tap.

https://gyazo.com/7460bfbe19132c091396491517fb9d2e