Mobile Network Sensing Using Positioning-Based Ground Truth Labeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current solutions for obtaining ground truth data for object detection in mobile communication networks are cumbersome and require significant computational effort, making it inefficient for normal operation, especially in integrated communication and sensing (ICaS and JCaS) systems where annotated data is scarce.
Innovation Solution
A method within a mobile communication network that integrates sensing and positioning functions to obtain ground truth data by receiving radiofrequency sensing reception signals, allowing the network to gather location information and label objects, thereby eliminating the need for dedicated positioning systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated positioning systems are used to obtain ground truth data for object detection, then measurement precision is improved, but device complexity and computational effort increase significantly
Solution Approach 1:
The patent combines positioning and sensing functions into a unified system where the positioning function provides location information that serves as ground truth data for the sensing function's object detection, eliminating the need for separate dedicated positioning systems
Solution Approach 2:
The positioning function is designed to serve dual purposes: providing location information for communication purposes and simultaneously providing ground truth data for sensing and object detection, making the system multi-functional and reducing overall complexity
2Measurement precision
If dedicated positioning systems are deployed to gather location information for object detection, then measurement precision is improved, but productivity and operational efficiency deteriorate due to high computational requirements
Solution Approach 1:
The positioning function within the mobile communication network automatically provides location information that serves as ground truth data for sensing operations, enabling the system to self-serve without requiring external dedicated positioning systems or extensive computational processing
3Manufacturing precision
If annotated data is collected using traditional methods for training machine learning models in sensing systems, then manufacturing precision of training data is improved, but loss of time and operational complexity increase
Solution Approach 1:
The positioning function continuously gathers and provides location information in advance that can be directly used as ground truth data for training machine learning models, eliminating the need for time-consuming manual annotation processes
Solution Approach 2:
The positioning function acts as an intermediary that bridges the gap between raw sensing data and annotated training data by automatically providing location information that labels the sensing data, streamlining the training data preparation process
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 generation of training data and model data for machine learning-based object detection, simplifying the configuration and reducing computational requirements by leveraging existing network components for ground truth data acquisition.
Implementation Method 1
the sensing-capable or sensing-enabled entity or functionality performs sensing by means of receiving radiofrequency sensing reception signals
Data Source
Figure 1~4
Figure 5
AI summary
The invention relates to a method for providing at least one sensing-related service and/or for generating training data and/or sensing model data by means of processing sensing-related data that is generated within or as part of a mobile communication network, wherein the mobile communication network comprises at least a sensing function and a positioning function, wherein, as part of the sensing function, the mobile communication network comprises a sensing-capable or sensing-enabled entity or functionality, wherein the sensing-capable or sensing-enabled entity or functionality performs sensing by means of receiving radiofrequency sensing reception signals based on which information is able to be obtained about an area related to, or in the vicinity of, the sensing-capable sensing-enabled entity or functionality, wherein, as part of the positioning function, the mobile communication network is able to provide location information regarding active objects of, or connected or related to or detectable by, the mobile communication network, wherein, in order to provide at least one sensing-related service and/or in order to generate training and/or sensing model data, the method comprises the following steps: -- in a first step, the sensing function performs sensing in an area related to, or in the vicinity of, the sensing-capable or sensing-enabled entity or functionality, -- in a second step, the positioning function gathers location information regarding active objects in the area related to, or in the vicinity of, the sensing-capable or sensing-enabled entity or functionality, -- in a third step, the sensing function receives the location information regarding the active objects and uses the location information to obtain ground truth data for labeling.