Ping An Insurance (Group) Company of China has patented a method for selecting image samples using artificial intelligence. The method involves training models with labeled samples, calculating information quantum scores, clustering samples, and selecting target samples for improved accuracy in sample selection. GlobalData’s report on Ping An Insurance (Group) Company of China gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Ping An Insurance (Group) Company of China, Digital lending was a key innovation area identified from patents. Ping An Insurance (Group) Company of China's grant share as of April 2024 was 22%. Grant share is based on the ratio of number of grants to total number of patents.
Method for selecting image samples using artificial intelligence
A recently granted patent (Publication Number: US11972601B2) discloses a method for selecting image samples using advanced models and algorithms. The method involves obtaining labeled image samples, constructing instance segmentation and score prediction models, training these models with labeled samples, calculating information quantum scores, extracting feature vectors, clustering samples, and selecting target image samples based on scores and clusters. The instance segmentation model includes a feature pyramid networks (FPN) backbone network, a region generation network, and a three-branch network. The score prediction model shares parameters and structure with the FPN backbone network and includes a score prediction network. The method aims to efficiently select image samples for various applications based on their characteristics and scores.
The patent also covers a computing device and a computer-readable storage medium implementing the method steps. The device includes a processor executing instructions stored in memory to carry out the image sample selection process. The training of the instance segmentation model involves inputting image samples, generating interesting regions, performing instance segmentation, and optimizing model parameters. Similarly, the training of the score prediction model includes inputting samples, generating regions, predicting scores, and optimizing network parameters. The method's innovative approach to selecting image samples based on advanced models and algorithms showcases a significant technological advancement in the field of image processing and analysis, with potential applications in various industries requiring image data processing and selection.
To know more about GlobalData’s detailed insights on Ping An Insurance (Group) Company of China, 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.
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.
