US 12,388,730 B2
Classifier model for determining a network status of a communication network from log data
Chin Lam Eng, Tokyo (JP); Yu Jia, Beijing (CN); Lichao Gui, Jiangsu (CN); Chee Wai Ng, Sydney (AU); and Philipp Frank, Madrid (ES)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Appl. No. 18/563,029
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed May 28, 2021, PCT No. PCT/CN2021/096723
§ 371(c)(1), (2) Date Nov. 21, 2023,
PCT Pub. No. WO2022/246793, PCT Pub. Date Dec. 1, 2022.
Prior Publication US 2024/0250886 A1, Jul. 25, 2024
Int. Cl. H04L 43/04 (2022.01); H04L 41/16 (2022.01)
CPC H04L 43/04 (2013.01) [H04L 41/16 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method performed by an apparatus for training a classifier model to determine a network status relating to a communication network and/or a wireless device from log data, the method comprising:
extracting, from first log data relating to operations of one or more wireless devices and/or nodes in the communication network, a plurality of textual elements and a plurality of numerical elements;
transforming the plurality of textual elements to a first vector space to determine respective textual element vectors;
transforming the plurality of numerical elements to a second vector space to determine respective numerical element vectors;
embedding and clustering the textual element vectors and the numerical element vectors to determine a plurality of clusters of embedded vectors, wherein the embedding comprises, for a plurality of wireless device sessions, embedding at least one textual element vector and at least one numerical element vector into a single embedded vector representing the particular wireless device session; and
training a classifier model to determine a network status from second log data, wherein the classifier model is trained using the plurality of clusters of embedded vectors,
wherein the step of embedding and clustering is performed iteratively to jointly reduce an embedding loss and a clustering loss.