Abstract
ChatRouter is a system and method for processing natural language user inputs to accurately classify them into one or more predefined intents and subsequently route them for appropriate handling within a multi-skill artificial intelligence (AI) architecture. The core of the invention lies in its unique combination of a large language model (LLM) guided by a specialized few-shot learning paradigm, a multi-intent detection capability, and a hierarchical priority-based routing mechanism. This system is designed to interpret diverse user phrasings and map them to specific actionable categories, even when multiple intents are present in a single input.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "ChatRouter: A System and Method for Hierarchical Intent Classification and Dynamic Routing in Multi-Skill AI Architectures", Technical Disclosure Commons, (October 07, 2025)
https://www.tdcommons.org/dpubs_series/8691