Method and system for accurately pushing dynamic information of smart city bus stop board
By constructing a query semantic representation structure with semantic role labeling and dependency relationships, and combining multi-level semantic association modeling and multi-hop reasoning, the shortcomings of existing information push systems in understanding natural language queries and scene states are solved, enabling accurate push of bus stop information, improving user experience and system adaptability.
Patent Information
- Application Number
- CN202610799329.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-04
- Publication Date
- 2026-07-10
- Estimated Expiration
- 2046-06-04
AI Technical Summary
Existing smart city bus stop information push systems cannot understand the deep semantics in natural language queries and lack collaborative modeling of scene status and query intent, resulting in a disconnect between pushed information and users' real needs, and failing to provide accurate services in dynamic environments.
The system collects passenger-input query requests and the scene status information of the bus stop signs, constructs a query semantic representation structure that includes semantic role labeling and dependency relationships, performs multi-hop reasoning in the public transportation knowledge association network through multi-level semantic association modeling, introduces scene feasibility constraints to generate candidate answers, and optimizes the pushed content through scene adaptability scores and interaction feedback data.
It enables accurate identification and dynamic information delivery of passengers' true intentions in complex urban transportation networks, improves the relevance and usability of information, lowers the threshold for passengers to understand, and enhances the robustness and personalized service capabilities of the system.