UnitedHealth Group had 27 patents in digitalization during Q4 2023. The UnitedHealth Group Inc filed patents in Q4 2023 related to natural language processing operations using attention-based text encoder machine learning models, generating feature stores in databases, retrieving relevant items for user queries using search engine machine learning models, performing natural language processing for generating guided summaries, and techniques for efficient and resilient network-wide supervision of hierarchically-segmented blockchain networks. These patents introduce innovative methods and systems for various technological applications. 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 digitalization as a theme is 44% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Natural language processing machine learning frameworks trained using multi-task training routines (Patent ID: US20230418880A1)

The patent filed by UnitedHealth Group Inc. describes a method, apparatus, and system for natural language processing using an attention-based text encoder machine learning model trained with a multi-task training routine involving two or more training tasks. The method involves generating word-wise embedded representations for document data objects, training the model using language modeling loss models, and optimizing parameter values based on training input document data objects with ground-truth labels. The model generates document classifications for unlabeled document data objects based on the embedded representations, and prediction-based actions are performed accordingly.

The patent claims detail a computer-implemented method, apparatus, and computer program product for generating document classifications using an attention-based text encoder machine learning model. The method involves training the model with language modeling tasks, such as word masking and next sentence prediction, and utilizing a bidirectional encoder representations from transformers machine learning model. The apparatus includes processors and memory configured to generate word-wise embedded representations, optimize parameter values, and classify documents based on the model. The computer program product consists of computer-readable program code portions for implementing the method, including generating embedded representations, training the model, and performing prediction-based actions. The document classification loss model used is a cross-entropy loss model, and the training process involves adjusting parameter values based on a sequential learning regularization factor.

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.