ViaSat had two patents in artificial intelligence during Q4 2023. ViaSat Inc has developed methods, systems, and devices for semiconductor package manufacture, specifically focusing on wirebond interconnections between the die and die substrate. This involves capturing input data during inspection, passing it to a machine learning engine to predict RF performance ratings, and selecting an optimal ML model through training data set processing. GlobalData’s report on ViaSat gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

ViaSat grant share with artificial intelligence as a theme is 0% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Semiconductor package inspection with predictive model for wirebond radio frequency performance (Patent ID: US20230360188A1)

The patent filed by ViaSat Inc. describes methods, systems, and devices for semiconductor package manufacture involving wirebond interconnections between a die and die substrate. The method includes capturing input data of wirebond features, processing it with a machine learning engine to predict radio-frequency (RF) performance ratings, and outputting the rating. The system includes monitoring equipment to capture data, a machine learning engine with a trained model, and an RF performance predictor tool to evaluate and output the predicted RF performance rating. The method and system aim to improve the inspection process and ensure the quality of semiconductor packages by utilizing machine learning technology.

The method further includes steps for rejecting or passing the manufacture of the package based on the predicted RF performance rating, generating alerts during the wirebonding assembly process, and capturing input data through optical or infrared camera devices and sensor systems. Additionally, the training dataset includes wirebond parameters, RF performance parameters, and RF rating labels from prior assemblies, with the trained model being a neural network model. The system also includes a machine learning engine with an inference stage, training stage, and a multi-layer neural network, such as a convolutional neural network (CNN). Overall, the patent focuses on leveraging machine learning techniques to enhance the inspection and quality control processes in semiconductor package manufacturing, particularly in assessing RF performance ratings.

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

Premium Insights


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.