User Intent Understating and Modeling for Health Oriented Search

Introduction

KP search engine provides search services specialized across various topics. Patients come to our search engine to look for information with different possible intents: reading health topics, food recipes, make a doctor appointment, etc. An accurate understanding of a user’s query intent can help improve the performance of downstream tasks such as query scoping and ranking. Queries are often ambiguous and can be interpreted in many ways, even by humans. Hence, semantic query understanding's primary objective is to understand the intention behind the query. This implies first predicting the language used to express the query. Second, parsing the query according to that language. Third, extracting the entities and concepts mentioned in the query. Finally, based on all this information, we predict one or more possible intentions with a certain probability, which is particularly important for ambiguous queries. Although there has been extensive research on query intent understanding in the areas of web search and ecommerce, it is still underexplored in healthcare.

Goal

Currently, there is no query intent understanding component in our search pipeline. In this project we plan to leverage the existing customer signals and build an AI-enabled query understanding system for KP which allows us to provide a better search experience to our members.