Human Security. has been granted a patent for a system that detects human and bot activity on webpages. The method involves collecting time-series data, classifying events, performing data transformations, and training a machine learning model to distinguish between bot and non-bot behaviors, including identifying false positives. GlobalData’s report on Human Security gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Human Security, Social data privacy protection was a key innovation area identified from patents. Human Security's grant share as of July 2024 was 77%. Grant share is based on the ratio of number of grants to total number of patents.

Bot and human activity detection on webpages

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

The patent US12063239B2 describes an apparatus and methods for analyzing events occurring on a webpage to distinguish between bot and non-bot behavior. The core of the invention involves a processor and memory configured to collect time-series data on webpage events, derive classifications, and perform functional transformations on this data. The apparatus is designed to identify potential features from the events, which are then used to train a machine learning model. This model is capable of determining the nature of the events—whether they are indicative of bot activity or not. Additionally, the system incorporates validation logic to assess the accuracy of the model, focusing on metrics such as false positive rates and performance across different browser environments and internet service providers.

The claims further detail the functionalities of the apparatus, including the ability to receive an array of events and their timing, and to perform specific transformations based on the type of data (numeric or categorical). For instance, the apparatus can execute mean transformations to analyze the time between keystrokes or count transformations to tally mouse movements. The methods outlined in the patent also emphasize the importance of error analysis during validation, ensuring that the machine learning model is robust and reliable in distinguishing between bot and non-bot behaviors. Overall, this patent presents a comprehensive approach to enhancing the detection of automated interactions on web platforms, leveraging machine learning and data analysis techniques.

To know more about GlobalData’s detailed insights on Human Security, 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

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.