IoT Device Classification From Network Traffic for Accurate Media Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing media exposure measurement systems struggle to accurately distinguish between Internet of Things (IoT) devices and devices used for digital media consumption, leading to inaccurate media consumption data and inefficient advertising decisions.
Innovation Solution
A method using network traffic data analysis with an IoT classification model, specifically a decision tree, to identify IoT devices by processing activity parameters such as user agent count, domain name count, and average bandwidth, allowing for the filtering out of IoT devices from network traffic data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If network traffic data is collected from all devices at a household, then comprehensive media exposure data can be gathered, but IoT devices without streaming capabilities contaminate the data and reduce measurement accuracy
Solution Approach 1:
The patent extracts and removes IoT devices from the network traffic data by classifying devices based on their network activity patterns. The system identifies devices lacking streaming capabilities (such as smart thermostats and cameras) and separates them from media consumption devices, thereby purifying the dataset for accurate media exposure measurement.
Solution Approach 2:
The patent changes the parameters used for device identification by analyzing network traffic characteristics such as user agent strings, domain names, and bandwidth patterns. These parameter changes enable the system to distinguish between IoT devices and media consumption devices based on their unique network behavior signatures.
2Measurement precision
If device classification is performed using complex analysis methods, then accurate identification of IoT devices is achieved, but computational resources and processing time increase
Solution Approach 1:
The patent transforms complex device identification into a parameter-based classification problem by extracting key network traffic features (user agent count, domain name count, average bandwidth). These transformed parameters enable accurate IoT device identification through simpler comparison logic rather than complex analysis methods.
Solution Approach 2:
The patent segments the device identification process into distinct steps: collecting network traffic data, extracting activity parameters, comparing parameters against thresholds, and classifying devices. This segmentation allows for efficient processing by breaking down the complex task into manageable, sequential operations.
3Ease of operation
If all devices are treated as media consumption devices, then device mapping is simplified, but media consumption data becomes inaccurate due to inclusion of non-streaming devices
Solution Approach 1:
The patent extracts and removes IoT devices from the media consumption device list by classifying devices based on their network activity patterns. The system identifies devices lacking streaming capabilities (such as smart thermostats and cameras) and separates them from media consumption devices, thereby purifying the dataset for accurate media exposure measurement.
Solution Approach 2:
The patent introduces an intermediary classification layer that mediates between raw network traffic data and final media consumption data. This intermediary layer processes network traffic characteristics to identify and filter out IoT devices, creating a clean subset of media consumption devices for accurate tracking.
Data Source
AI summary
In one example, a method is described. The method includes: obtaining network traffic data characterizing network activity of devices coupled to a network at a media exposure measurement location, processing the network traffic data to generate, for each of multiple devices: activity parameters, each characterizing a network activity of the device, processing the activity parameters using an IoT classification model that includes a decision tree having: (i) multiple internal nodes, each internal node associated with an activity parameter threshold, and (ii) multiple leaf nodes, each leaf node associated with either the IoT device type or the other device type, based on the decision tree, selecting, from the device identifiers included in the network traffic data, a target device identifier corresponding to a leaf node in the decision tree that is associated with the IoT device type, and outputting the target device identifier.