The invention relates to a method for anonymizing vehicle data for the use of vehicle-external services (FES). The method according to the invention is characterized in that, within a fleet (10) of vehicles (11, 12, 13, 14) of the same type with an inhomogeneous group of vehicle users, a first variable, which is at least indirectly dependent on an integer number n of recorded vehicle sensor values, and a second variable, which is at least indirectly dependent on an integer number m of present vehicle sensor values, is measured for each of the vehicles (11, 12, 13, 14), wherein similarities are determined for at least one of the variables of multiple or all vehicles (11, 12, 13, 14) in the fleet (10), after which the vehicles (11, 12, 13, 14) are categorized into a class that is similar in terms of the similarity of the at least one variable or into a dissimilar class, wherein, if a vehicle-external service (FES) is requested, instead of the variable (5) of the requesting vehicle (11) that contains the information relevant to the service, the corresponding variable (6) of a vehicle (12) from the class of similar vehicles (12), a computationally ascertained variable from the applicable variables of multiple vehicles (12) from the class of similar vehicles (12) or an artificially generated similar variable is transmitted.
VERFAHREN ZUR ANONYMISIERUNG VON FAHRZEUGDATEN
METHOD FOR ANONYMIZING VEHICLE DATA
PROCÉDÉ D'ANONYMISATION DE DONNÉES DE VÉHICULE
2024-06-12
Patent
Electronic Resource
German
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G07C TIME OR ATTENDANCE REGISTERS , Zeit- oder Anwesenheitskontrollgeräte / H04L TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION , Übertragung digitaler Information, z.B. Telegrafieverkehr |
Verteiltes Machine-Learning-Modell zur Kompression und Anonymisierung von übertragenen Fahrzeugdaten
European Patent Office | 2024
|