- Challenges in Personalized Ranking
Traditional ranking algorithms struggle to fully utilize multimodal information (e.g., text, images, video) and have limited model complexity, failing to meet users’ demands for precise and personalized search results.
- Challenges in Ultra-Large-Scale Retrieval
In retrieval scenarios with candidate libraries containing hundreds of billions of entries, traditional discriminative models face issues such as insufficient model capacity and low indexing efficiency, urgently requiring next-generation retrieval algorithms.
- Challenges in Complex Query Understanding
User search intents are becoming increasingly complex. Traditional search engines struggle to accurately interpret the semantics of long/complex sentences and polysemous queries, leading to low satisfaction with search results.
- Challenges in Resource Utilization
The storage-computation separation architecture of search systems results in low resource utilization. Optimizing resource usage while maintaining performance has become a critical issue.
- Necessity of Large Model-Based Intelligent Search
Introducing large model technologies is essential to address the above challenges. It can significantly enhance the semantic understanding, retrieval efficiency, and resource utilization of search systems, thereby delivering more accurate and efficient search experiences to users.