AI Positioning Model Orchestration for Precise 5G UE Location
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication systems lack detailed methods and procedures for precise terminal positioning using artificial intelligence (AI), which is essential for enhancing the quality of service in mobile communication systems.
Innovation Solution
An AI-based positioning method that involves receiving a positioning request from a consumer network function, collecting data for an AI positioning model, generating location information, and transmitting it to the consumer network function, with support from a location management function selected by an access and mobility management function, and potentially training or retraining the model using data collected from user equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI-based positioning is implemented in mobile communication systems, then positioning precision is improved, but system complexity increases due to lack of defined methods and procedures
Solution Approach 1:
The patent segments the positioning system into distinct functional modules: consumer NF receives positioning requests, LMF selects and manages AI positioning models, NFs collect and provide positioning data, and AI models perform inference. This modular segmentation resolves the technical contradiction by organizing the complex AI-based positioning system into manageable, standardized components with defined interfaces, thereby reducing overall system complexity while maintaining high positioning precision
Solution Approach 2:
The patent introduces new parameters and parameters with new meanings to the mobile communication system to enable AI-based positioning. This includes adding AI model identification information to positioning requests, introducing model selection criteria parameters, and defining new data formats for AI model input/output. These parameter changes provide the necessary flexibility to implement precise AI-based positioning while maintaining system manageability through standardized parameter definitions
2Measurement precision
If AI positioning models are trained and deployed for precise positioning, then positioning accuracy is improved, but data collection and model training requirements increase system complexity
Solution Approach 1:
The patent makes the LMF a universal component that handles multiple functions: selecting AI positioning models, collecting positioning data from multiple sources, managing model training requirements, and performing inference. This multi-functionality resolves the technical contradiction by centralizing complex AI model management tasks in a single standardized component, thereby reducing overall system complexity while enabling precise positioning through comprehensive data collection and model training
Solution Approach 2:
The patent implements preliminary actions by having the LMF proactively collect positioning data from multiple NFs before AI model inference is needed, and by pre-managing AI model selection and training requirements. This preliminary data collection and model preparation resolves the technical contradiction by organizing complex data gathering and training activities in advance through standardized procedures, reducing the complexity of on-demand AI positioning while maintaining high accuracy
3Reliability
If existing mobile communication systems are enhanced with AI positioning, then service quality is improved, but compatibility with legacy systems may be compromised
Solution Approach 1:
The patent introduces the LMF as an intermediary component between legacy positioning infrastructure and new AI positioning models. The LMF receives positioning requests from consumer NFs, selects appropriate AI models, collects data from various sources including legacy positioning systems, and provides unified positioning outputs. This intermediary role resolves the technical contradiction by enabling AI-based positioning with high service quality while maintaining compatibility with existing mobile communication systems through standardized interfaces and gradual integration
Solution Approach 2:
The patent implements dynamic model selection where the LMF can choose different AI positioning models based on available data, service requirements, and model performance. The system dynamically adapts between AI-based positioning and legacy positioning methods, and can update AI models as new models become available or performance requirements change. This dynamic adaptability resolves the technical contradiction by providing high service quality through AI positioning while maintaining flexibility and compatibility with legacy systems
Data Source
AI summary
An artificial intelligence (AI)-based positioning method and a device for performing the same are disclosed. According to an embodiment, the AI-based positioning method includes receiving a request for positioning of a user equipment (UE) from a consumer network function (NF), among legacy positioning and AI-based positioning, determining to perform the AI-based positioning for the positioning, receiving information of an AI positioning model for the AI-based positioning from a fifth generation (5G) core (5GC) NF, collecting data for a learning and inference operation of the AI positioning model from the 5GC NF, generating location information of the UE by performing the AI-based positioning based on the received information and the collected data, and transmitting the generated location information to the consumer NF.