Illumina had 50 patents in artificial intelligence during Q1 2024.Illumina Inc’s patents in Q1 2024 focus on methods for extracting information from datasets using optical character recognition, assigning quality scores to bases called by a neural network-based base caller, marking duplicate fragments in genomic data, classifying cancer conditions using convolutional neural networks, and artificial intelligence-based base calling for sequencing data. These technologies aim to improve data analysis and classification processes in genomics and document processing. GlobalData’s report on Illumina gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Illumina grant share with artificial intelligence as a theme is 22% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Systems and methods for automated classification of a document (Patent ID: US20240070170A1)
The patent filed by Illumina Inc. describes a method for extracting information from a dataset, such as a document, by receiving the dataset at an information handling device, extracting textual information using optical character recognition, and classifying the dataset into one of multiple classes based on similarity scores calculated for different window regions of the dataset. The method involves training a machine-learning model to classify documents into classes by receiving a training dataset with associated classes, identifying focus words, extracting text regions containing these words, and training the model to establish associations between documents and classes using the extracted text regions. The training process includes computing training relevance metrics, applying them to the model, and optimizing hyperparameters through iterative grid search algorithms.
The system described in the patent includes a computer system with memory storing instructions and a processor executing these instructions to receive a training dataset, identify focus words, extract text regions, and train a machine-learning model to classify documents into classes based on the associations established through the extracted text regions. The system can handle different types of free text documents, such as medical reports or breast imaging reports, with classes like fatty, scattered fibroglandular density, heterogeneously dense, extremely dense, and indeterminate. Additionally, the system computes training relevance metrics, applies them to the model by assigning weights to documents, and optimizes hyperparameters using iterative grid search algorithms to enhance the accuracy of the machine-learning model.
To know more about GlobalData’s detailed insights on Illumina, 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.