Bayerische Motoren Werke Aktiengesellschaft

Nokia Technologies Oy

Jesper Olsen

Jilei Tian

Happia Cao

Won Tchoi

The present disclosure relates to a concept for training one or more model parameters of a predictive parking difficulty model for different locations based on collected telemetry data. A ground truth ranking related to subjective parking difficulties at the different locations is obtained based on pairwise comparison of parking difficulties between pairs of the different locations by one or more humans. A prediction loss between a model ranking of the different locations obtained by the predictive parking difficulty model and the ground truth ranking is determined. The one or more model parameters are adjusted to minimize the prediction loss between the model ranking and the ground truth ranking.

Methods and apparatuses for training one or more model parameters of a predictive parking difficulty model

A navigation system includes primary and secondary navigation device, and a server. The secondary navigation device transmits geolocation data to the server. The primary navigation device receives user input indicating a destination. The primary navigation device also determines a current route to the destination based on a current location of the primary navigation device, and transmits the current route to the server. The primary navigation device also receives and displays a difficulty index from the server in response to transmitting the current route. The server determines historical routes reflecting historical commutes based on the geolocation data. The server also determines the difficulty index based on the one or more historical routes and the current route, and transmits the difficulty index to the primary navigation device in response to receiving the current route.

Systems and methods for recognizing and measuring hard-to-reach destinations

An approach is provided for training a device to associate user, object or device context information with a user defined context. The context information platform receives recorded context information from a device. The associated recorded context information is then associated with the context to enable training of a context model associated with the context.

Method and apparatus for determining user context

An apparatus for providing compound models for speech recognition adaptation. The apparatus may include processor and memory including computer program code with the memory, the computer program code being configured, with the processor, to cause the apparatus to at least receive a speech signal corresponding to a particular speaker. The apparatus may further be configured to select a cluster model including both a speaker independent portion and a speaker dependent portion based at least in part on a characteristic of speech of the particular speaker. The apparatus may be further configured to process the speech using the selected cluster model. The apparatus may be further configured to cause at least a speaker dependent portion of one or more non-selected cluster models to be stored remotely. A corresponding method and computer program product are also provided.

Growing community of inventors

Beijing, China

Jesper Olsen