SDP Signaling for AI Model Selection in 5G Media Services
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 5G mobile communication systems face challenges in supporting AI/ML media services due to limitations in compatibility between UE devices and application providers, processing power constraints, and synchronization issues between media data streams and AI/ML model data streams, especially for dynamic media applications like conversational and streaming services.
Innovation Solution
The implementation of a method and apparatus that utilize SDP signaling to enable UE and MRF entities to identify, select, and deliver AI/ML models based on media data types and services, ensuring compatibility and synchronization through the use of new parameters for SDP signaling, allowing for the selection and delivery of required AI/ML models and data streams using RTP and SCTP protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If AI/ML models are delivered to UE for media service processing, then media service functionality is enhanced, but compatibility issues between UE devices and application providers arise
Solution Approach 1:
The patent introduces SDP (Session Description Protocol) as an intermediary mechanism that mediates between UE devices and application providers. SDP enables standardized negotiation and description of AI/ML model parameters, media types, and service requirements, creating a common language that ensures compatibility while allowing enhanced functionality. The protocol acts as a mediator that translates between different UE capabilities and provider requirements.
Solution Approach 2:
The patent employs parameter changes by dynamically adjusting AI/ML model parameters, data types, and processing configurations based on UE capabilities and service requirements. Through SDP signaling, the system can adapt model parameters in real-time to match available computational resources and media characteristics, enabling functionality enhancement while maintaining compatibility through flexible parameter negotiation.
2Adaptability or versatility
If multiple AI models are offered to UE, then service versatility is improved, but complexity in model selection and synchronization increases
Solution Approach 1:
The patent segments the AI/ML model delivery process into distinct components using SDP protocol elements. Each AI model is described as a separate entity with its own parameters, data types, and synchronization requirements. This segmentation allows the UE to process and select from multiple models systematically, reducing overall complexity by breaking down the selection and synchronization tasks into manageable segments through standardized protocol handling.
3Productivity
If AI/ML model data streams are synchronized with media data streams, then service performance is improved, but synchronization complexity and latency increase
Solution Approach 1:
The patent applies preliminary action by establishing synchronization parameters and model data stream configurations before actual media processing begins. Through SDP offer and answer procedures, the UE and server negotiate synchronization mechanisms in advance, pre-configuring timing relationships and data flow coordination. This preliminary setup reduces real-time synchronization complexity and latency by establishing the framework before data processing starts.
Data Source
AI summary
The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. Methods and apparatuses in provided in which a session description protocol (SDP) offer including a list of artificial intelligence (AI) models is received from a media resource function (MRF) entity. At least one AI model is identified from the list for outputting at least one result using first media data, based on a type of the first media data and a media service in which the at least one result is used. An SDP response is transmitted to the MRF entity, requesting the at least one AI model as a response to the SDP offer, and the first media data is processed based on the at least one AI model received from the MRF entity.