UnitedHealth Group had 37 patents in artificial intelligence during Q3 2023. UnitedHealth Group Inc filed patents in Q3 2023 for various methods and systems related to predictive data analysis and machine learning. One patent focuses on using a machine learning framework to perform predictive data analysis operations, including a predictive event embedding machine learning model and a network-based inference machine learning model. Another patent involves a method for tracking and notifying the progress of individuals transitioning from candidate to onboarded status in an organization. Additionally, there are patents related to predicting sensitive information in interactive voice sessions and performing context-based document classification prediction using a hierarchical attention-based keyword classifier machine learning framework. GlobalData’s report on UnitedHealth Group gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

UnitedHealth Group grant share with artificial intelligence as a theme is 49% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Network-based inference machine learning models (Patent ID: US20230273974A1)

The patent filed by UnitedHealth Group Inc. describes methods, apparatus, systems, and computing devices for performing predictive data analysis using a machine learning framework. The framework consists of a predictive event embedding machine learning model and a network-based inference machine learning model. The goal is to generate a cross-event classification for a predictive entity.

The method involves identifying a plurality of predictive events associated with the predictive entity. For each predictive event, a predictive event embedding is generated using a predictive event embedding machine learning model. An event relationship network data object is then generated for the predictive entity, which includes predictive event embeddings, event relationship links, and relationship embeddings. The event relationship network data object is used to generate final predictive event embeddings and final relationship embeddings using a network-based inference machine learning model. These embeddings are determined based on a sequence of L sequential network update layers.

Based on the final embeddings, a cross-event classification is generated. This classification can be generated by generating a per-event classification for each predictive event based on the final predictive event embeddings and then generating the cross-event classification based on these per-event classifications. The per-event classification can be determined by comparing values of the final predictive event embedding to a threshold value or by selecting a predictive event significance classification based on the maximal value position indicator.

The method also includes performing prediction-based actions based on the cross-event classification. The apparatus for implementing this method includes at least one processor and memory, while the computer program product includes computer-readable program code portions stored in a non-transitory computer-readable storage medium.

In summary, the patent describes a method, apparatus, and computer program product for performing predictive data analysis using a machine learning framework. The framework involves generating predictive event embeddings and an event relationship network data object, and using a network-based inference machine learning model to generate final embeddings. These embeddings are then used to generate a cross-event classification, which can be used to perform prediction-based actions.

To know more about GlobalData’s detailed insights on UnitedHealth Group, buy the report here.

Premium 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.