Mobile Network Sensing Inference Pipeline for Multi-Use Services
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication networks lack a unified framework to efficiently process sensing-related data for diverse use cases, limiting their applicability beyond specific applications like autonomous driving, and require separate optimization for each use case.
Innovation Solution
A method and system for processing sensing-related data within mobile communication networks, involving first and second sensing-capable entities, with data cascading through sensing edge and application servers to generate generalized inference data, supporting diverse use cases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensing data is processed locally at base stations and user equipment for specific applications like autonomous driving, then measurement precision is improved, but device complexity increases and processing burden on cellular infrastructure grows
Solution Approach 1:
The patent introduces an intermediary processing layer between the sensing entities (base stations and user equipment) and the application layer. This intermediary performs data fusion, filtering, and preliminary analysis, reducing the complexity burden on individual devices while maintaining high measurement precision through distributed processing architecture.
Solution Approach 2:
The sensing data processing is segmented into multiple stages: local processing at base stations and user equipment for initial data collection and filtering, intermediate processing for data fusion and coordination, and final processing for application-specific inference. This segmentation distributes complexity across multiple components while preserving measurement accuracy at each stage.
2Measurement precision
If separate optimization is performed for each sensing use case, then measurement precision for specific applications is improved, but adaptability to diverse use cases deteriorates
Solution Approach 1:
The patent implements a universal sensing data processing framework that can accommodate multiple sensing applications (autonomous driving, gesture recognition, environmental monitoring, etc.) through a common infrastructure. The system provides multi-functionality by allowing different applications to utilize the same processed sensing data with application-specific parameters and algorithms, thereby maintaining precision across diverse use cases without requiring separate optimized systems.
3Ease of manufacture
If sensing services are provided using existing cellular infrastructure, then ease of manufacture is improved, but productivity of sensing service delivery deteriorates due to lack of unified framework
Solution Approach 1:
The patent introduces a dynamic sensing service framework that adapts the processing pipeline and resource allocation based on service requirements, data types, and network conditions. This dynamic approach enables the existing cellular infrastructure to efficiently deliver diverse sensing services by dynamically adjusting processing priorities, resource distribution, and data flow routing, thereby improving productivity without requiring complete system redesign.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient, cost-effective provision of sensing services in cellular mobile broadband networks, capable of serving multiple and diverse use cases while leveraging existing cellular system architecture, and reducing application-specific processing burdens on base stations and user equipment.
Implementation Method 1
the at least one sensing-capable or sensing-enabled entity or functionality transmits a radiofrequency sensing signal, wherein, as a result of the radiofrequency sensing signal being transmitted, a radiofrequency sensing reception signal is received
Data Source
AI summary
A method for providing at least one sensing-related service by means of processing sensing-related data that is generated within or as part of a mobile communication network includes: in a first step, first stage sensing inference data are provided to at least one sensing edge server, wherein the at least one sensing edge server generates second stage sensing inference data; and in a second step, the second stage sensing inference data are provided to at least one sensing application server, wherein the at least one sensing application server provides sensing-related services and/or generates sensing application data.