Skip to main content
Uber logo

Schedule rides in advance

Reserve a rideReserve a ride

Schedule rides in advance

Reserve a rideReserve a ride
Data / ML, Engineering

Food Discovery with Uber Eats: Building a Query Understanding Engine

June 10, 2018 / Global
Featured image for Food Discovery with Uber Eats: Building a Query Understanding Engine
Figure 1: A high-level view of a graph data pipeline shows how graphs are created with multiple data sources.
Figure 2: Our sample ontology describes semantic relationships between different entity types in the graph.
Figure 3: A subgraph of our overall ontology illustrates the relationship between cuisines and dish types.
Figure 4: Using query2vec, a search query leads to an order from a restaurant if there is a concrete line that connects them. For example, “Spicy food” and “Tan Tan Noodle” both lead to an order from restaurant “Hunan Noodle House.” As a result, we say those two queries appeared in the same context.
Figure 5: “Tan Tan Noodle” expands to three queries that further retrieve a set of relevant restaurant.
Ferras Hamad

Ferras Hamad

Ferras Hamad is an Engineer at Uber focused on search and ranking within the Uber Eats app. He is a graduate of Carnegie Mellon University with a degree in Computer Science.

Isaac Liu

Isaac Liu

Isaac Liu was an engineer at Uber focused on search and recommendations within the Uber Eats app. He holds a Ph.D. in Electrical Engineering and Computer Science from UC Berkeley.

Xian Xing Zhang

Xian Xing Zhang

Xian Xing is a data science manager on the UberEverything team.

Posted by Ferras Hamad, Isaac Liu, Xian Xing Zhang