Here Global B.v.

Gavin Brown

Elena Vidyakina

Ori Dov

Olivier Dousse

Stefano Bennati

Elena Mumford

Aleksandra Kovacevic

Johannes Braese

Dmitry Skripin

Arshak Grigoryan

Tom Phelan

Nam Tran Duc

Elena Van Leeuwen

Embodiments described herein relate to anonymizing of trajectories of mobile devices through the obfuscation of stay points. Methods may include: receiving probe data points of a trajectory in real-time or near real-time from a probe apparatus as it travels along the trajectory; calculating, for each probe data point, a probability of the trajectory reaching a stay point within a predetermined distance; providing sequential sub-sets of probe data points of the trajectory to a location-based service provider in response to the sequential sub-sets of probe data points including probe data points having a probability failing to satisfy a predetermined value; and identifying a potentially last sub-set of probe data points of the sequential sub-sets of probe data points to provide to the location-based service provider in response to identifying a probe data point having a probability of the trajectory reaching a stay point within the predetermined distance satisfying the predetermined value.

Method, apparatus, and computer program product for anonymizing trajectories and stay points

Embodiments described herein relate to anonymizing of trajectories of mobile devices. Methods may include: receiving an input chunk of probe data points, where the input chunk includes probe data points spanning an input duration, where the input chunk represents at least a first input portion of a trajectory; generating, based at least in part on the input chunk, an output chunk of one or more probe data points, where the output chunk includes one or more probe data points spanning an output duration, where the output duration is different from the input duration, where the output chunk represents at least an output portion of the trajectory, where the first input portion of the trajectory and the output portion of the trajectory share at least a common portion of the trajectory; and providing the output chunk of one or more probe data points to a location-based service provider.

Method, apparatus, and computer program product for anonymizing trajectories

Embodiments described herein relate to anonymizing of trajectories of mobile devices through the obfuscation of stay points. Methods may include: receiving probe data points of a trajectory in real-time or near real-time from a probe apparatus as it travels along the trajectory; calculating, for each probe data point, a probability of the trajectory reaching a stay point within a predetermined distance; providing sequential sub-sets of probe data points of the trajectory to a location-based service provider in response to the sequential sub-sets of probe data points including probe data points having a probability failing to satisfy a predetermined value; and identifying a last sub-set of probe data points of the sequential sub-sets of probe data points to provide to the location-based service provider in response to identifying a probe data point having a probability of the trajectory reaching a stay point within the predetermined distance satisfying the predetermined value.

Embodiments described herein relate to anonymizing of trajectories of mobile devices through the introduction of gaps between sub-trajectories. Methods may include: receiving a set of probe data points defining a trajectory; identifying a temporal length range of sub-trajectories; receiving a mode, where the mode is established based on a preceding set of probe data points defining a trajectory, where the mode includes an indication of whether to generate a sub-trajectory or a gap from the beginning of the received set of probe data points; and establishing at least one sub-trajectory including a sub-set of the set of probe data points, where the at least one sub-trajectory is established to satisfy the temporal length range of sub-trajectories.

An approach is disclosed for a data-driven evaluation of heuristics for trajectory cropping. The approach involves, e.g., determining a cropping heuristic, wherein the cropping heuristic comprises an algorithm for cropping a probe trajectory collected from one or more sensors of a mobile device to anonymize the probe trajectory data. The approach also involves processing the probe trajectory using the cropping heuristic to generate a cropped probe trajectory. The approach further involves extracting one or more heuristic-based features of the cropped probe trajectory data. The approach also involves extracting one or more privacy-based features from a privacy preference, wherein the one or more privacy-based features represent a target level of cropping to meet the privacy preference. The approach further involves computing a score based on a distance between the one or more heuristic-based features and the one or more privacy-based features. The approach further involves providing the score as an output.

Method, apparatus, and system for data-driven evaluation of heuristics for trajectory cropping

Methods are provided for modeling mobility based on one or more devices of the user. Methods may include: receiving at least a portion of a first mobility model from a first device, where the first mobility model may be established based on learning algorithms performed on the first device; updating a shared mobility model to become a first shared mobility model based on the at least a portion of the first mobility model; providing the first shared mobility model to the first device; receiving at least a portion of a second mobility model from a second device, where the second mobility model may be established based on learning algorithms performed on the second device; updating the first shared mobility model to become a second shared mobility model based on the at least a portion of the second mobility model; and providing the second shared mobility model to the second device.

Growing community of inventors

Berlin, Germany

Gavin Brown