Qualcomm had five patents in edge computing during Q1 2024. Qualcomm Inc’s patent involves methods, systems, and apparatuses for updating or retraining machine learning models using edge ground truth data from edge devices. This process includes obtaining datasets from trained machine learning processes, transmitting them to edge devices, receiving updated datasets, and updating the original dataset with the new information to improve the machine learning model. GlobalData’s report on Qualcomm gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Qualcomm had no grants in edge computing as a theme in Q1 2024.
Recent Patents
Application: Apparatus and methods for generating edge ground truth data for a federated system architecture using machine learning processes (Patent ID: US20240096058A1)
The patent filed by Qualcomm Inc. describes methods, systems, and apparatuses for updating or retraining a trained machine learning model/process based on edge ground truth data generated by edge devices. The apparatus includes a communications interface, a storage medium storing instructions, and a processor. The processor is configured to obtain datasets of trained machine learning processes from a database, transmit messages to edge devices, receive ground truth data generated by the edge devices, retrain the machine learning process based on the ground truth data, and update the datasets accordingly. The apparatus can also transmit updated datasets to other edge devices for further processing.
Furthermore, the apparatus allows for the comparison of ground truth data generated by different edge devices to identify discrepancies, which are used to update the machine learning process. The apparatus can handle various types of object detection and recognition processes, such as bounding box, semantic segmentation, instance segmentation, and panoptic segmentation. Additionally, the apparatus enables the retraining of machine learning processes based on discrepancies and consistency data received from other edge devices or a local datacenter. Overall, the patent outlines a comprehensive system for updating and retraining machine learning models based on edge ground truth data, facilitating improved accuracy and performance in object detection and recognition tasks across multiple edge devices.
To know more about GlobalData’s detailed insights on Qualcomm, 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, 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.
