Skip to main content
Uber logo

Schedule rides in advance

Reserve a rideReserve a ride

Schedule rides in advance

Reserve a rideReserve a ride
Uber AI

Improving Driver Communication through One-Click Chat, Uber’s Smart Reply System

September 28, 2018 / Global
Featured image for Improving Driver Communication through One-Click Chat, Uber’s Smart Reply System
Figure 1: With one-click chat, driver-partners can more easily respond to rider messages.
Figure 2: The architecture for Uber’s smart reply system, OCC, consists of a five-step workflow.
Figure 3: The machine learning algorithm empowers the flow of the OCC experience. Two key steps are involved: 1) intent detection and 2) reply retrieval.
Figure 4: The UberChat back-end service manages the flow of messages between senders and receivers.
Figure 5: Behind the scenes of OCC, our machine learning system relies on two workflows, offline training and online serving.
Figure 6: This two-dimensional t-SNE projection of the Doc2vec word embedding illustrates the ability of the model to automatically organize concepts and learn implicitly the relationships between words, clustering them based on semantics.
Figure 7: In this two-dimensional t-SNE projection of sentence embedding, the model clusters messages around intent.
Yue Weng

Yue Weng

Yue Weng is a senior data scientist on Uber's Conversational AI team working on projects in the domains of deep learning, natural language processing, conversational AI systems, streaming analytics, and real-time monitoring systems.

Huaixiu Zheng

Huaixiu Zheng

Huaixiu Zheng is a senior data scientist at Uber, working on projects in the domains of deep learning, reinforcement learning, natural language processing and conversational AI systems.

Anwaya Aras

Anwaya Aras

Anwaya is a software engineer on Uber's Communications Platform team. Prior to her current role, she was a fraud engineer on Uber's Risk & Safety team.

Franziska Bell

Franziska Bell

Fran Bell is a Data Science Director at Uber, leading platform data science teams including Applied Machine Learning, Forecasting, and Natural Language Understanding.

Posted by Yue Weng, Huaixiu Zheng, Anwaya Aras, Franziska Bell

Category: