Extreme Networks. has been granted a patent for a method that reduces storage space in tracking network endpoint behavior. The method involves creating behavior models by encoding network flow records, utilizing hash tables, and employing a Document to Vector algorithm to analyze and store these models for ongoing behavior tracking. GlobalData’s report on Extreme Networks gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Extreme Networks, VPN tunneling was a key innovation area identified from patents. Extreme Networks's grant share as of June 2024 was 81%. Grant share is based on the ratio of number of grants to total number of patents.
Reducing storage for tracking network endpoint behavior
The patent US11996986B2 outlines a method and system designed to optimize the storage space required for tracking the behavior of network endpoints. The method involves several key steps, including determining a record for a single network flow, extracting relevant fields, and encoding these fields into a flow word. This flow word is then assigned to a block in a hash table, which corresponds to the network endpoint. A linked list is created for the block, where the flow word is added. The method further generates an endpoint vector that represents the behavior model of the network endpoint by concatenating flow words and utilizing a Document to Vector (doc2vec) algorithm. The behavior model is stored in memory, and anomalous behavior is detected by comparing the endpoint vector against a normalcy threshold in a multidimensional space.
Additionally, the patent describes various enhancements to the method, such as detecting unknown network endpoints and adding corresponding blocks to the hash table. The generation of the behavior model can be triggered by accumulating a threshold number of flow words. The system can also identify idle modules to assist in generating the endpoint vector. Tracking of the network endpoint's behavior over time is facilitated through techniques like Kalman filtering and deriving multivariate Gaussian distributions to ascertain the current position of the endpoint vector in the multidimensional space. The patent also includes provisions for a non-transitory computer-readable medium that contains instructions for executing these operations, ensuring that the method can be implemented in a computing environment.
To know more about GlobalData’s detailed insights on Extreme Networks, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
