Machine learning methods
By using a second learning model when different judgment processing results are inconsistent, training data related to anomalies is generated, which solves the problem of insufficient training data in the prior art and improves the accuracy of anomaly detection in machine learning.
CN122090194APending Publication Date: 2026-05-26TOYOTA JIDOSHA KK
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2025-11-24
- Publication Date
- 2026-05-26
Smart Images
Figure CN122090194A_ABST
Abstract
A machine learning method. An information processing device determines the presence or absence of an object in a camera image based on time-series data of the image using a first determination process. Next, the information processing device determines the presence or absence of the object in the camera image based on the time-series data using a second determination process employing a first learning model. If the results related to the presence or absence of the object differ between the first and second determination processes, the information processing device executes a third determination process to determine the presence or absence of the object in the camera image using the second learning model. Then, the information processing device adds the camera image to the first learning model based on the result of the third determination process.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Teacher data generation device, teacher data generation method, teacher data generation program, and object detection system
JP2018200531A