Mapbox, Inc.

Morgan Herlocker

Lily Chai

David Michael Thompson

Laurier Rochon

Camille Teicheira

A method for avoiding likely one-way segments of roads in route planning is described. In selecting an optimal route, the cost of a possible route is computed by adding the costs associated with the segments along the route. Cost is a metric that is associated with the total expense to traverse a route in order to determine whether the route should be chosen over another. Each segment of a road is associated with a cost factor that represents the traffic condition of the segment. For a given segment, automobile traces that traveled the segment are counted. A ratio of traces traveled in one direction to traces traveled in the opposite direction is determined. If the ratio is below a certain threshold, the segment of the road is regarded as likely one-way. The original cost factor is replaced with a new cost factor that penalizes the segment in routing calculations.

Dynamic one-way street detection and routing penalties

In an embodiment, a data processing method providing an improvement in filtering telemetry data received from mobile devices comprises receiving, from a mobile device, telemetry data comprising a plurality of probes, each probe identifying a location of the mobile device at a time of the probe, wherein the plurality of probes form first digital trace data identifying a path of the mobile device; determining, for a particular probe of the plurality of probes, a first attribute of the particular probe; determining whether the first attribute of the particular probe satisfies a first threshold; in response to satisfying the first threshold, deleting the particular probe from the plurality of probes and dividing the first digital trace data into second digital trace data and third digital trace data; performing an action using the second digital trace data and the third digital trace data.

Filtering noise values from telemetry data

A method for providing an improvement in speed estimation for route planning involves identifying a plurality of observed speeds for a segment of road during a first time period, the plurality of observed speeds corresponding to the plurality of traces of the segment of road. The method further involves identifying a plurality of discrete values in the plurality of observed speeds, and determining a count for each of the plurality of discrete values. The method further involves aggregating the counts for the plurality of traces including the segment to create aggregated counts for the segment, and determining the speed estimate from the aggregated counts for the plurality of traces including the segment.

Generating accurate speed estimations using aggregated telemetry data

A trace comprising location data about a computing device is received at a mapping server, where the trace stores the location data about the computing device in an ordered set of points. The origin and destination of the trace are obscured. Then, the trace is then separated into a set of subtraces by dividing the received points of location data into a set of subtraces, and removing the links between subtraces of the set of subtraces. For example, subtraces can be divided based on size, distance, elapsed time, or features of interest present in the location data.

Anonymization of geographic route trace data

Digital data corresponding to a trace by a device is received. The digital data includes location data and time data obtained over a period of time and representing movement of the device. A set of derived values for the plurality of metrics are calculated from the sets of values corresponding to the metrics, and the set of derived values are compared to a binary classification model to determine whether the received digital data represents movement of a first type. The binary classification model was trained using a first set of traces representing the first type of movement and a second set of traces. In response to determining that the digital data represents movement of the first type, the received digital data corresponding to the trace is labelled with the first type of movement.

PU classifier for detection of travel mode associated with computing devices

Digital data corresponding to a trace by a device is received. The digital data includes a set of values for each of a plurality of metrics. A set of derived values for the plurality of metrics are calculated from the sets of values corresponding to the metrics, and the set of derived values are compared to a machine learning model trained using a plurality of travel modes. A plurality of confidence scores for the derived values are calculated. The plurality of confidence scores correspond to the plurality of travel modes. In response to a confidence score for a first travel mode of the plurality of confidence scores for the plurality of travel modes meeting a threshold value for the first travel mode, the received digital data corresponding to the trace is labelled with the first travel mode.

Detection of travel mode associated with computing devices

A method comprises identifying, in an electronic map, road data and intersection data, wherein the intersection data specifies an approach and two or more exits from the approach, bounding the approach using a bounding box around the entrance to an approach, identifying, using the bounding box, traces associated with the approach, wherein each trace identifies a path of a vehicle on one or more of the roads, for each trace of the plurality of traces, identifying which of the two or more exits most closely matches the particular trace, generating histograms based on a time period and which of the two or more exits most closely matches each trace of the plurality of traces, determining, using the histograms, whether one or more threshold values associated with one of the two or more exits is satisfied, sending a notification signal when the one or more threshold values is satisfied.

Growing community of inventors

Oakland, CA, United States of America

Morgan Herlocker