Network Device Client Identifier Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network user visibility methods often result in bandwidth issues and user dissatisfaction due to the need for multiple devices to make determinations outside of network devices, which can lead to inefficient network resource allocation and poor user experience.
Innovation Solution
Implementing machine learning on network devices to continuously learn and recognize patterns in user behavior and network traffic, allowing for enhanced network user visibility and improved resource allocation by classifying unique client device identifiers based on statistical properties and attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If multiple devices are used to make determinations outside of network devices, then network user visibility is improved, but bandwidth issues and user dissatisfaction occur due to inefficient network resource allocation
Solution Approach 1:
The patent consolidates the determination function into the network device itself, merging the visibility analysis capability with the existing network infrastructure. This eliminates the need for multiple external devices and enables direct processing of network traffic data at the network device, improving both visibility and resource allocation efficiency simultaneously
2Loss of information
If machine learning is implemented on network devices, then network user visibility and resource allocation are improved, but device complexity increases
Solution Approach 1:
The network device performs self-learning through machine learning algorithms, automatically analyzing network traffic patterns and making determinations without requiring external training or manual configuration. This self-service capability enables the device to adapt to changing network conditions while maintaining operational simplicity for users
Solution Approach 2:
The machine learning model is pre-configured with initial parameters and training data, enabling the network device to perform accurate determinations from the outset. This preliminary preparation reduces the complexity of ongoing operations by establishing a solid foundation for automated decision-making
Data Source
AI summary
An example method can include tracking, by a network device, a plurality of attributes associated with a plurality of unique client device identifiers stored in a tracking table; deriving, by the network device, a training data set based on the plurality of attributes; and generating, by the network device, a plurality of clusters by inputting the derived training data set to an unsupervised machine learning mechanism. The example method can include receiving, by the network device, a labeling of the plurality of unique client device identifiers in the tracking table based at least on the plurality of clusters; generating, by the network device, a plurality of classifiers by inputting the labelled tracking table to a supervised machine learning mechanism; and classifying, by the network device, a new unique client device identifier in the tracking table based at least on the plurality of classifiers.