Telefonaktiebolaget Lm Ericsson (publ)

Tracy Hu

Qingyan Liu

Richard Carlsson

Sky Zhao

The disclosure provides a method () and apparatus for anomaly detection in a network. The method () comprises: obtaining (S) a stream of time-series data related to the network; and dividing (S) the stream into a number of sub-streams each corresponding to a category of data. The method further comprises, for each of the sub-streams: reconstructing (S) a plurality of phase spaces; predicting (S), in each of the plurality of phase spaces, whether a data item in the sub-stream is an anomaly candidate based on a prediction model associated with the phase space; and detecting (S) the data item as an anomaly when it is predicted as an anomaly candidate in all of the plurality of phase spaces.

Method and apparatus for anomaly detection in a network

A method and apparatus for handling location data in a mobile communications network. A network node obtains an average geographical location of a mobile device over a predetermined time period and uses the average geographical location in an area of interest in an Origin Destination matrix. The advantage of using an average geographical location over a period of time is that much less data needs to be stored compared to storing all geographical data, but the data can be reused to define new Origin Destination matrices.

Growing community of inventors

Beijing, China

Tracy Hu