Zhejiang Geely Holding Group had 41 patents in artificial intelligence during Q1 2024. The Zhejiang Geely Holding Group Co Ltd has filed patents related to updating perception functions of vehicles with Automated Driving Systems, controlling charging of electric vehicles based on the presence of a portable device, generating soundscape based on environmental and vehicle data, updating perception functions using machine-learning algorithms, and managing safety features of vehicles through input interfaces controlled by vehicle occupants. GlobalData’s report on Zhejiang Geely Holding Group gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Zhejiang Geely Holding Group grant share with artificial intelligence as a theme is 24% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Method and system for in-vehicle self-supervised training of perception functions for an automated driving system (Patent ID: US20240062553A1)
The patent filed by Zhejiang Geely Holding Group Co Ltd. describes a method for updating the perception function of a vehicle with an Automated Driving System (ADS) using machine learning algorithms. The process involves obtaining an image of the vehicle's surrounding environment, processing it to detect objects or free-space areas, creating an evaluation dataset with masked permutations of detected objects, calculating reconstruction error values for each evaluation image, and updating the machine-learning algorithm based on the image and the evaluation image with the highest error value. The method aims to improve the accuracy of object detection in the vehicle's perception module by iteratively updating the machine-learning algorithm.
Additionally, the patent includes claims for different aspects of the method, such as indicating detected objects with bounding boxes or masking regions, permuting indications differently in each evaluation image, updating model parameters based on anomalous image data, and transmitting updated parameters to a remote entity for global updates. The system described in the patent includes control circuitry to carry out the method steps, forming evaluation datasets, processing images with machine-learning algorithms, selecting evaluation images, and updating perception modules. The patent also covers a non-transitory computer-readable storage medium with instructions for executing the method and a vehicle equipped with the system for updating perception functions based on the described method. Overall, the patent focuses on enhancing the accuracy and efficiency of object detection in vehicles with ADS through iterative machine learning updates and evaluation processes.
To know more about GlobalData’s detailed insights on Zhejiang Geely Holding Group, 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.