Fortinet has patented a system for natural language message categorization using a vector space model to identify text from a specific topic. The method involves calculating normal exclusion values for unique words, forming a message vector, and comparing it to category extremes for real-time topic determination. GlobalData’s report on Fortinet gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Fortinet, was a key innovation area identified from patents. Fortinet's grant share as of April 2024 was 72%. Grant share is based on the ratio of number of grants to total number of patents.

Natural language message categorization based on vector space model

Source: United States Patent and Trademark Office (USPTO). Credit: Fortinet Inc

A recently granted patent (Publication Number: US11971983B2) outlines a method for classifying natural language messages using a unique approach. The method involves receiving a message containing text content, calculating normal exclusion values for each unique word based on their frequency in the message and a dictionary, and forming a message vector. This vector is then compared to category extremes to determine if the message belongs to a specific category of interest. The patent details the equations and processes involved in this classification method, emphasizing the use of a large dictionary, such as the Oxford English Corpus™, and the importance of accurate frequency calculations for unique words.

Furthermore, the patent extends beyond just the method and describes a system for characterizing message categories, including a processing resource and a computer-readable medium with stored instructions. The system follows a similar process of calculating normal exclusion values, forming message vectors, and comparing them to category extremes to determine inclusion in a specific category. The patent also highlights the importance of accessing vector definitions and category extremes from storage mediums for accurate classification. Overall, the patent provides a detailed and technical insight into a method and system for classifying natural language messages based on unique word frequencies and dictionary comparisons, offering a novel approach to message categorization in the field of natural language processing.

To know more about GlobalData’s detailed insights on Fortinet, 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.