Expired50% confidenceFactExact time
The Xiaodu Health Screen adopts a hybrid architecture of cloud-based large models plus local wake-up, where the local lightweight model parameter count is typically in the millions for wake-word detection, and complex tasks are completed by calling cloud-based large models via API.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
Sources
Related Claims
UnverifiedSmart devices typically adopt a hybrid architecture of cloud-based large models plus local wake-word detection, where simple commands are processed locally and complex multi-turn dialogues call cloud large model APIs.83% similarUnverifiedUsing local models for simple tasks and cloud models for complex tasks is the optimal cost-effectiveness strategy.70% similarUnverifiedFor sensitive, core, and compliance-related tasks, local large language models and open-source solutions should be prioritized, while cloud-based AI tools can be used for public, low-risk tasks.69% similarUnverifiedThe vast majority of current mainstream AI programming assistants use cloud-based large model architectures, where user input is sent to the service provider's servers for processing.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/338039API
curl https://kongchang.com/api/v1/knowledge/claims/338039MCP
get_claim(id=338039)