AI-Aware Resource Indicators for Wireless Communication Reliability

The patent combines wireless channel conditions and AI parameters into a unified resource indication framework. The network device determines resource indications by considering both the wireless channel state information and the terminal's AI processing capabilities simultaneously, rather than treating them as separate factors. This merging ensures that resource allocation decisions account for both communication efficiency and AI task quality requirements.

The patent introduces a new parameter dimension by integrating AI parameters (such as AI model complexity, processing requirements) with traditional wireless communication parameters (channel quality, signal strength). This parameter expansion allows the system to adapt resource allocation dynamically based on the combined state of both communication conditions and AI task requirements, resolving the contradiction between communication efficiency and AI task quality.

The network device performs joint determination of resource indications by simultaneously evaluating both AI parameters and wireless channel conditions. The resource allocation decision process integrates information about AI model requirements with real-time channel state information, ensuring that neither factor is optimized at the expense of the other. This combined approach prevents the degradation of communication efficiency that would result from AI-parameter-only optimization.

The patent implements dynamic resource allocation that adapts to changing conditions in both the wireless channel and AI task requirements. The system continuously updates resource indications based on current channel state information and AI parameter states, allowing flexible adjustment of communication resources to match the combined demands of both communication efficiency and AI task quality at any given moment.

The patent segments the resource indication process into distinct components: the terminal reports AI parameters and receives channel state information, the network device processes this segmented information separately before integrating it into unified resource allocations. This segmentation allows the system to manage complexity by handling different parameter types through dedicated processing paths while still achieving comprehensive resource indications.

The network device acts as an intermediary that receives separate inputs (terminal AI parameters and channel state information), processes them through a unified determination mechanism, and produces integrated resource allocations. This intermediary role allows the system to incorporate comprehensive information without proportionally increasing overall system complexity, as the network device centralizes the integration logic.