Verint Systems. has been granted a patent for a method that automates the selection of anomaly detection techniques for various classes of time series data. The process involves classifying datasets, filtering detection methods, and evaluating their effectiveness to recommend the most suitable method for identifying anomalies. GlobalData’s report on Verint Systems gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Verint Systems, Network traffic analysis was a key innovation area identified from patents. Verint Systems's grant share as of July 2024 was 61%. Grant share is based on the ratio of number of grants to total number of patents.

Anomaly detection method selection for time series data

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

The patent US12032543B2 outlines a method and system for automatically determining an appropriate anomaly detection method tailored for specific classes of time series data. The process begins with a processor receiving multiple datasets, each linked to distinct predefined time series characteristics and classified into known categories based on their expected properties. The processor then identifies a subset of anomaly detection methods relevant to these known classes, filtering from a larger pool of methods. An anomaly detection score is calculated for each method based on the occurrence of false positives and false negatives, utilizing a sliding window approach across all datasets. This score is then compared against a calculated threshold to recommend the most suitable anomaly detection method for further application on similar time series data.

The claims further detail that the known classes may include factors such as seasonality, trend, concept drift, or missing time steps. The anomaly detection scores can be derived from metrics like the windowed F-score or the Numenta anomaly benchmark (NAB) score. Additionally, the datasets may be pre-annotated to identify anomalies, with some datasets containing unlabeled data during a probationary period. The system is designed to accommodate various types of anomalies, including collective, point, and contextual types, and utilizes a diverse array of anomaly detection methods, such as windowed Gaussian, SARIMAX, and Facebook Prophet, among others. This comprehensive approach aims to enhance the accuracy and efficiency of anomaly detection in time series analysis across different domains.

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