Nice had five patents in cybersecurity during Q2 2024. Nice Ltd filed patents for a computerized method to train and apply a Machine Learning textual behavioral identification model for authenticating agents in a digital multi-channel environment, as well as a method for sensitive data redaction from screenshots. The first method involves training the ML model using historical interactions, receiving textual responses from agents, and calculating an imposter probability score in real-time. The second method includes grouping screenshots by common features, calculating scores for pixels, blackening pixels with high scores to redact sensitive data, and storing the redacted screenshots in a database. GlobalData’s report on Nice gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Nice had no grants in cybersecurity as a theme in Q2 2024.

Recent Patents

Application: Computerized-method and computerized-system for training and applying a machine learning (ML) textual behavioral identification model to authenticate an agent, in a digital multi-channel environment (Patent ID: US20240203424A1)

The patent filed by Nice Ltd. describes a computerized method for training and applying a Machine Learning (ML) textual behavioral identification model to authenticate agents in a digital multi-channel environment. The method involves training the model using historical interactions in a controlled environment, generating profile-identity data for each agent, receiving textual responses from agents during interactions, calculating an imposter-probability score in real-time, and taking actions based on the score. The system includes processors, a pattern-identification data store, and a file management system to facilitate the authentication process and actions based on the imposter-probability score.

The method also involves creating textual units, finding distributions of n-grams, embedding vocabulary elements using Natural Language Processing (NLP), arranging n-gram graph distributions, and calculating average distances to determine the imposter-probability score. The system is designed to prompt agents for authentication, block them from further interactions, or send reports/alerts to supervisors based on the imposter-probability score. Additionally, the system can retrain the ML model using recent data and dispose of aged training data to ensure accurate authentication of agents in the digital multi-channel environment.

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