METHOD AND DEVICE FOR RECOGNIZING ANOMALIES IN A D

专利名称：METHOD AND DEVICE FOR RECOGNIZING

ANOMALIES IN A DATA STREAM OF ACOMMUNICATION NETWORK

发明人：Antonio La Marca,Markus Hanselmann,Thilo

Strauss

申请号：US16213649申请日：20181207

公开号：US20190199743A1公开日：20190627

专利附图：

摘要：A method for the automatic recognition of anomalies in a data stream in a

communication network. The method includes providing a trained variational

autoencoder that is trained on non-faulty data packets, with specification of a referencedistribution of latent quantities, indicated by reference distribution parameters;determining one or more distribution parameters as a function of an input quantityvector applied to the trained variational autoencoder, which vector is determined by oneor more data packets; and recognizing the one or more data packets as anomalous datapacket(s) as a function of the one or more distribution parameters.

申请人：Robert Bosch GmbH

地址：Stuttgart DE

国籍：DE

更多信息请下载全文后查看