METHOD AND SYSTEM FOR ROUTING PATH SELECTION

A method and system for selecting routing paths are provided. The routing path comprises a route and at least one characteristic from a set of characteristics. The method logs data of selected routing paths in response to requests from client devices to collect historical data of selecting routing p...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	BELGANI, CHAKIB, BARRIER, ANTHONY ALEXIS GHISLAIN, NANTY, SIMON, VIOLLET, ERWAN, LE TOQUIN, YOURI THIBAULT MARIE
Format:	Patent
Sprache:	eng ; fre
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A method and system for selecting routing paths are provided. The routing path comprises a route and at least one characteristic from a set of characteristics. The method logs data of selected routing paths in response to requests from client devices to collect historical data of selecting routing paths and stores the data of selected routing paths in a data storage. Thereafter, a machine learning model is trained on the historical data of selecting routing paths received from the data storage. The output of the machine learning model is a selection prediction for the routing path. In response to a new request from a client device, a set of routes fulfilling the request is determined in order to determine a set of routing paths by combining the set of routes with characteristics from the set of characteristics. The trained machine learning model is applied on the set of routing paths to determine a subset of routing paths for which the selection prediction is higher than a threshold. Details of the subset of routing paths are then queried and valid routing paths determined. Finally, the details of at least a subset of the valid routing paths are returned to the client device.