Recent changes
EPO Patent Granted: Breach Prediction via Machine Learning
The European Patent Office has granted patent EP4498271B1 for a method of breach prediction using machine learning. The patent, which lists Deepen Desai, Dianhuan Lin, and Rex Shang as inventors, was granted on March 18, 2026. This grant pertains to advancements in AI and computing, specifically within the G06N classification.
EPO Patent EP4498271C0: Machine Learning Breach Prediction
The European Patent Office has published patent EP4498271C0 concerning machine learning for breach prediction. This patent, granted to inventors Deepen Desai, Dianhuan Lin, and Rex Shang, is effective March 18, 2026, and applies to designated states within the European Union.
Method for training machine learning model using selected data
Method for training machine learning model using selected data
EPO Patent Granted: Robot Action Correction Determination and Utilization
The European Patent Office has granted patent EP4219088B1, which covers methods for determining and utilizing corrections to robot actions. This patent is related to artificial intelligence and machine learning applications in robotics.
EPO Patent Application: Method for Correcting Ground Truth Labels in Training Datasets
The European Patent Office has published patent application EP4711990A1 detailing a method for correcting ground truth labels in training datasets for machine learning models used in computer vision tasks. The application, filed by AUMOVIO Germany GmbH, describes a process involving training a model, modifying sample images, obtaining predicted labels, and then correcting the ground truth labels based on a comparison.
EPO Patent Application: AI Model Training System
The European Patent Office published patent application EP4711939A1 concerning systems and methods for training artificial intelligence models and storing checkpoint files. The application, filed by Alipay (Hangzhou) Information Technology Co., Ltd., details a system with a model training module and a cache module designed to efficiently manage datasets and AI model checkpoints.
Huawei Cloud Patent: Model Inference Method
The European Patent Office has published patent application EP4711986A1 by Huawei Cloud, detailing a model inference method. This method aims to improve data security and inference efficiency by having clients and servers process different parts of user data separately.
Parametric Curve Scanning Method for Photovoltaic String and Converter
The European Patent Office has published a patent application by Huawei Digital Power Technologies Co., Ltd. for a parametric curve scanning method for photovoltaic strings and converters. This method aims to efficiently determine if scanned curves are affected by light changes without requiring additional hardware.
Cell Balancing Method and Battery System
The European Patent Office has published patent application EP4712296A1 for a cell balancing method and battery system developed by LG Energy Solution, Ltd. The invention details a method for managing battery cell balancing in low-power modes to optimize energy consumption and performance.
EPO Patent Publication EP4712269A1: Multi-antenna and Power Receiving Device
The European Patent Office has published patent application EP4712269A1 for a multi-antenna and power receiving device, filed by Aeterlink Corp. The patent describes a specific antenna element configuration designed to improve power reception efficiency.
Last 7 days
Most active sources
Browse Categories
Activity
Get daily alerts
Morning digest delivered to your inbox. Free.
Free. Unsubscribe anytime.
Categories
Data Privacy & Cybersecurity
13 sources
Banking & Finance
13 sources
Pharma & Drug Safety
9 sources
Trade & Sanctions
8 sources
Telecom & Technology
7 sources
Consumer Protection
4 sources
Healthcare
4 sources
Government & Legislation
3 sources
Energy
3 sources
Insurance
3 sources
Courts & Legal
2 sources
Environment
1 sources
Securities & Markets
1 sources
Get European Union alerts
Daily digest of regulatory changes. AI-summarized, no noise.
Free. Unsubscribe anytime.