KR KR20250025339A

METHOD AND APPARATUS FOR TRAINING AN ARTIFICIAL INTELLIGENCE MODEL TO ANOMALY DETECTION OF UNMANNED MOVING OBJECTS

Abstract

According to an embodiment of the present disclosure, provided is a method for training a model for anomaly detection, which is performed by a computing device. the method comprises the steps of: obtaining a plurality of sensor data from each of a plurality of sensors related to an unmanned moving object; performing preprocessing for aligning and compressing the plurality of sensor data based on time; generating a plurality of composite data from the plurality of preprocessed sensor data using an artificial intelligence-based pre-trained data augmentation model; and training an artificial intelligence-based anomaly detection model using the plurality of preprocessed sensor data and the plurality of composite data.

Classification

Source documents

Does this actually block you?

A document turning up in a search is not the same as a document that anticipates your claims. Our registered Patent Agents read the claims, not just the abstract, and tell you where you still have room.

Protect Your Invention

Bibliographic data via the European Patent Office's Open Patent Services (DOCDB) . Republished here for research and prior-art review. This page is not legal advice, and its presence in our index says nothing about the validity or enforceability of the document. For the Indian legal position (status, oppositions, renewals), see InPASS.