Zilliz logo
user icon

Xiaomi’s Smart News Aggregator

Xiaomi is a global electronics company that manufactures and invests in smartphones, mobile applications, laptops, home appliances, laptops, and many other products. The company ships its smartphones with a home brewed web browser that has a news aggregator embedded within it. To consistently make content recommendations that appeal to individual users Xiaomi leveraged artificial intelligence (AI).

Milvus, an open-source vector database built by Zilliz, is used to power the core recommendation engine inside Xiaomi's smart news aggregator.

Objective

Build a mobile news aggregator that automatically recommends relevant content based on user profiles, search history, engagement, and more.

Challenges

  • Recommendations must remain relevant amid evolving user preferences and interests.
  • The recommendation system must be capable of incorporating massive volumes of news content that is published each second.
  • Useful content recommendations require an ideal balance between speed and precision, so any index used must be fast and maintain a high degree of accuracy.

Why Milvus

  • Near real-time search allows query results to be returned instantaneously and recently published content to be made immediately available for search.
  • Support for most mainstream vector indexes makes Milvus highly flexible, capable of providing an ideal solution for almost any application scenario.

Results

  • Content recommendation served in milliseconds thanks to efficient similarity search on trillion-scale datasets.

"Without Milvus, building our news aggregator wouldn't have been possible. The platform maintains consistent performance levels even in situations with unusually high concurrency."

- Jie Yuan, Recommendation Algorithm Architect at Xiaomi