AI Data Request Event Triggers for Timely Network Transmission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems lack a method for timely transmission of AI data between network devices, hindering effective data collection and utilization for network performance enhancement.
Innovation Solution
A data transmission method involving network devices that send AI data requests with event information to trigger data transmission based on specific AI events, allowing for timely and efficient collection of AI data needed for training, inference, or optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If AI data transmission is implemented without event-triggered mechanisms, then data can be transmitted continuously, but signaling overhead increases and unnecessary data transmission occurs
Solution Approach 1:
The patent applies preliminary action by pre-configuring event information (event identifiers, thresholds, conditions) in the AI data request before actual data transmission occurs. This allows the network device to automatically trigger transmissions only when predefined events occur, eliminating the need for continuous signaling and reducing overhead while maintaining efficient data collection.
2Reliability
If AI data is transmitted continuously between network devices, then data availability is improved, but energy consumption and network load increase
Solution Approach 1:
The patent implements periodic action through event-triggered data transmission, where AI data is transmitted only when specific events occur (such as threshold violations, state changes, or predefined conditions). This replaces continuous transmission with intermittent, event-driven transmissions, ensuring data availability when needed while significantly reducing energy consumption and network load during stable periods.
3Measurement precision
If event information is included in every AI data request, then transmission accuracy is improved, but message size and processing complexity increase
Solution Approach 1:
The patent applies the extraction principle by separating event information into two parts: essential event identifiers are included in AI data requests, while detailed event configuration parameters are stored separately in the network device. This extraction reduces message size and processing complexity in requests while maintaining accurate event detection through the retained identifiers and pre-stored configuration.
Data Source
AI summary
Example data transmission methods and apparatuses are described. In one example method, when sending an artificial intelligence (AI) data request to a second network device, a first network device includes event information of a first AI event in the AI data request, where the first AI event is an event that triggers the second network device to send AI data. In this way, when detecting that the first AI event is satisfied, the second network device sends, in a timely manner based on the event information of the first AI event, AI data needed by the first network device, thereby satisfying diversified data requirements of the first network device.