1. A semantic search engine which really understands the content and context. Applied to e-commerce, news, video domains.

2. Deep learning based method to learn from rich user interaction data to find the relevance between content and context.

3. Natural language processing algorithms including intent classification, entity recognition and knowledge graph matching algorithms to analyze and understand the meaning of text.

4. Personalization algorithms which learns from a user's search history and preferences to tailor search results to their individual needs.