Granted Patent B2

US 12,523,485 · App. 18/566,056 · Granted Jan 13, 2026

Inventors: Daniel Kotzor (Seefeld, DE); Stefan Holder (Munich, DE)

Assignee: Bayerische Motoren Werke Aktiengesellschaft

G01C21/3617

Abstract

Claims (30)

1 . A method for providing a route-specific service to a user of a vehicle, the method including:

receiving a set of driven navigation routes of the vehicle;

identifying navigation route clusters using the set of driven navigation routes of the vehicle;

training a machine learning method using the identified navigation route clusters as training data;

receiving a characteristic of a current journey of the vehicle;

predicting a probability for each identified navigation route cluster of the vehicle depending on the received characteristic of the current journey of the vehicle using the trained machine learning method;

identifying a navigation route cluster with the highest predicted probability;

providing the route-specific service to the user of the vehicle for the current journey of the vehicle if the navigation route cluster with the highest predicted probability has a probability value that exceeds a predetermined threshold value.

2 . The method as claimed in claim 1 , wherein the set of driven navigation routes includes driven navigation routes of a user of the vehicle.

3 . The method as claimed in claim 1 , wherein the set of driven navigation routes contains driven navigation routes of all users of the vehicle.

4 . The method as claimed in claim 1 , wherein at least one navigation route cluster is representative of one or more driven navigation routes from the set of driven navigation routes, the distance of which is less than or equal to a maximum, predetermined distance.

5 . The method as claimed in claim 1 , wherein a cost function is used during the training of the machine learning method, with which an adjustment of hyperparameters of the machine learning method is evaluated by a hyperparameter optimization method.

6 . The method as claimed in claim 5 , wherein at least one navigation route cluster is representative of one or more driven navigation routes from the set of driven navigation routes, the distance of which is less than or equal to a maximum, predetermined distance.

7 . The method as claimed in claim 5 , wherein the hyperparameters of the machine learning method are adjusted until a preferably global maximum of the cost function is reached.

8 . The method as claimed in claim 7 , wherein the cost function evaluates the adjustment of the hyperparameters of the machine learning method by means of at least two parameters.

9 . The method as claimed in claim 8 , wherein a first parameter of the at least two parameters is representative of a display frequency or a frequency of provision of the route-specific service.

10 . The method as claimed in claim 9 , wherein at least one navigation route cluster is representative of one or more driven navigation routes from the set of driven navigation routes, the distance of which is less than or equal to a maximum, predetermined distance.

11 . The method as claimed in claim 9 , wherein a second parameter of the at least two parameters is representative of a prediction accuracy of the predicted probability.

12 . The method as claimed in claim 8 , wherein one of the at least two parameters is representative of a prediction accuracy of the predicted probability.

13 . The method as claimed in claim 1 , wherein the identification of a navigation route cluster with the highest predicted probability involves an identification of navigation route clusters with the n highest predicted probabilities, with n=1, 2, 3.

14 . The method as claimed in claim 1 , wherein the route-specific service is provided for the navigation route clusters with the n highest predicted probabilities.

15 . A computer-readable medium for providing a route-specific service to a user of a vehicle, wherein the computer-readable medium contains instructions which, when executed on a computer or a control unit, carry out the method as claimed in claim 1 .

16 . A system for providing a route-specific service to a user of a vehicle, wherein the system is designed to carry out the method as claimed in claim 1 .

17 . A vehicle containing the system for providing a route-specific service to a user of a vehicle as claimed in claim 16 .

18 . A mobile terminal containing the system for providing a route-specific service to a user of a vehicle as claimed in claim 16 .

19 . The method of claim 1 wherein the navigation route cluster having the highest predicted probability corresponds to a predicted navigation route, and wherein providing the route-specific service further comprises at least one of the group consisting of:

using the vehicle to communicate to the user traffic congestion information for the predicted navigation route;

using the vehicle to communicate to the user at least one suggestion for an alternative navigation route;

preconditioning vehicle components for an upcoming road condition of the predicted navigation route; and

operating vehicle components to perform a driver assistance function based on the predicted navigation route based on the navigation route cluster with the highest predicted probability.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (16)