BT Group has patented a computer-implemented method for detecting anomalous behavior in a computer network. The method involves accessing data records, generating training data for a neural network, and comparing vector representations to identify changes indicating abnormal network behavior. GlobalData’s report on BT Group gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on BT Group, Cloud gaming was a key innovation area identified from patents. BT Group's grant share as of April 2024 was 50%. Grant share is based on the ratio of number of grants to total number of patents.

Detecting anomalous behavior in computer networks using neural networks

Source: United States Patent and Trademark Office (USPTO). Credit: BT Group Plc

A recently granted patent (Publication Number: US11973778B2) discloses a computer-implemented method for detecting anomalous behavior within a computer network. The method involves accessing data records related to communication occurrences in the network, generating training data items for a neural network, training the neural network using the training data, and comparing multiple generations of vector representations to identify anomalous changes in behavior. The system aims to enhance network security by detecting and responding to unusual activities effectively.

In addition to detecting anomalous behavior, the method also includes implementing protective measures in response to identified changes in the network. These protective measures may involve deploying or configuring firewalls, anti-malware facilities, antivirus facilities, adjusting security monitoring levels, or selectively disconnecting computer systems from the network. The attributes of communication considered in the method include source and destination addresses, communication ports, protocol identifiers, communication size, number of packets, network protocol flags, timestamps, and durations. The neural network utilized in the method features a single layer of hidden units and employs techniques such as augmenting training data and performing vector similarity functions to enhance anomaly detection capabilities. Overall, the patented method offers a comprehensive approach to network security through advanced anomaly detection and response mechanisms.

To know more about GlobalData’s detailed insights on BT Group, buy the report here.

Premium Insights


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.