Traffic Monitoring via RF Signal Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for inferring real-time road traffic conditions are either manual, require extensive infrastructure, or rely on smartphone and in-vehicle sensor data, which may not provide comprehensive or dynamic traffic insights.

Innovation Solution

A computer system comprising network nodes and a machine learning model that uses radio frequency characteristics and performance management counters to infer traffic parameters such as vehicle flow rate and type, enabling dynamic traffic management without specific infrastructure or excessive human resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual traffic counting methods are used, then human observers can visually count and report traffic, but this method is labor-intensive and cannot provide real-time comprehensive traffic insights

Engineering Contradiction:
Improvetraffic condition accuracyVSAvoidhuman resource requirement
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system enables traffic monitoring to serve itself by utilizing existing radio frequency signals already present in the environment. Network nodes automatically detect and analyze these signals to infer traffic parameters without requiring manual intervention or additional specialized infrastructure, making the system self-sufficient and eliminating labor-intensive manual counting

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical counting methods with automated electronic detection systems. Network nodes use radio frequency signal analysis to automatically detect vehicle presence and characteristics, substituting human observers and manual tallying with electronic sensors and machine learning algorithms that process signal data to infer traffic flow, vehicle types, and congestion levels

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automatic traffic counting devices are installed, then electronic sensors can detect and tally traffic, but this requires extensive infrastructure installation on road surfaces

Engineering Contradiction:
Improvetraffic monitoring capabilityVSAvoidinfrastructure requirement
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system makes existing network nodes perform multiple functions: they continue their primary communication network function while simultaneously serving as traffic monitoring sensors. By analyzing radio frequency signals already being transmitted for communication purposes, the same infrastructure provides both network connectivity and traffic monitoring capabilities, eliminating the need for separate dedicated traffic counting devices

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent uses radio frequency signals as an intermediary carrier that conveys both communication data and traffic information. Instead of requiring direct physical contact sensors on road surfaces, the system extracts traffic parameters from intermediary radio signals that naturally propagate through the environment, allowing indirect but effective traffic detection without intrusive infrastructure

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If smartphone and in-vehicle sensor data are collected, then GPS coordinates can track users and vehicles, but this data may not provide comprehensive traffic insights or dynamic traffic management capability

Engineering Contradiction:
Improvetraffic data completenessVSAvoiddata collection system
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system replaces GPS-based tracking with radio frequency signal analysis. Instead of relying on devices carried by users and vehicles to report position, the infrastructure-based network nodes passively detect traffic by analyzing characteristics of radio signals in the environment, providing comprehensive area-wide coverage without requiring participation from individual devices

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The traffic monitoring system serves itself by utilizing radio frequency signals that already exist in the environment for communication purposes. The same signals used for network communication automatically provide traffic information when analyzed by network nodes, eliminating the need for separate data collection devices in vehicles or smartphones

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4186049B1Method and computer system determining a representation of a parameter
Publication Date: 2025.05.21 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
  • EP4186049B1 patent drawingFigure 1
  • EP4186049B1 patent drawingFigure 2
  • EP4186049B1 patent drawingFigure 3

AI summary

A method and a computer system (001) for determine a representation of at least one area. The computer system comprises a plurality of nodes, and at least one machine learning model (002). Representation parameters may be associated with an environmental categorization of the area. The method comprises training (S31) a machine learning model, receiving (S32) information, obtaining (S33) an inferred representation parameter, and enabling the sending (S34) of the parameter. The training of the machine learning model can be achieved by using a set of training data where the data is representing a radio frequency characteristic, or a performance management counter. The information received is in the form of a radio frequency characteristic (006) or a performance management counter (007). The obtaining of the parameter associated with the environmental categorization is performed by using the machine learning model and the received information.