SailPoint Technologies. has been granted a patent for a method that enhances machine learning model training in AI systems. The method involves generating identity graphs from identity management data, applying drift detection models, and determining whether to continue, incrementally train, or replace the machine learning model based on drift measures. GlobalData’s report on SailPoint Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on SailPoint Technologies, was a key innovation area identified from patents. SailPoint Technologies's grant share as of July 2024 was 71%. Grant share is based on the ratio of number of grants to total number of patents.
Incremental training of machine learning models using drift detection
The patent US12056588B2 outlines a method for generating and utilizing an identity graph within a distributed enterprise computing environment. This process begins with the collection of identity management data from various systems, which includes information on entitlements (access rights) and identities. The identity graph is constructed by creating nodes for each identity and entitlement, and edges are established to represent the relationships between them. The method further involves deriving datasets from the identity graph at different times, training a machine learning model based on the initial dataset, and subsequently applying a drift detection model to assess changes between datasets over time. Depending on the drift measure obtained, the system can either continue using the existing model, incrementally train it with new data, or replace it with a new model.
Additionally, the patent describes the implementation of a non-transitory computer-readable medium that contains instructions for executing the aforementioned method. It emphasizes the importance of graph embedding techniques to generate datasets and includes provisions for comparing drift measures against a predefined threshold. If the drift exceeds this threshold, the system is designed to alert users about potential data drift, ensuring timely responses to changes in the identity management landscape. The claims also highlight the integration of a drift prediction model, which is trained on the initial dataset to enhance the accuracy of drift detection. Overall, the patent presents a comprehensive approach to identity management that leverages machine learning and graph theory to maintain the integrity and relevance of identity data in dynamic enterprise environments.
To know more about GlobalData’s detailed insights on SailPoint Technologies, 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, 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.
