Abstract: Aspects of the disclosure relate to using machine learning methods for customized output generation. A computing platform may train a model (using historical data) by classifying the historical data by a trip context, a device interaction context, and physical condition context, or a personality context, and training models using the classified historical data. The computing platform may monitor a data source system to collect new data, which may include information about multiple drivers. The computing platform may generate, by inputting the new data into the model, a customized driving output for a first driver, where the customized driving output is based at least in part on information about a second driver. The computing platform may send, to a computing device, the customized driving output and commands directing the computing device to display the customized driving output, which may cause the computing device to display the customized driving output.

Abstract: Methods, computer-readable media, software, and system may generally build and quantify mobility patterns based on user location data, both at an individual level and an aggregate level. The system may determine the origin and destination data for each trip taken by a user. The system may then define areas of mobility using a mobility graph built from the data. The graph may include nodes and edges. In some examples, the nodes are constructed from the origins and destinations of the trajectories using spatial clustering techniques. Further, the edges between nodes may be constructed based on the trips between them, such as two nodes are connected by an edge if there is at least one trip between them. The edges may be given different weights based on trip frequencies. The system may then determine a region of mobility using the generated mobility graph and data clustering techniques.

Abstract: Aspects of the disclosure relate to using machine learning methods for customized output generation. A computing platform may train a model (using historical data) by classifying the historical data by a trip context, a device interaction context, and physical condition context, or a personality context, and training models using the classified historical data. The computing platform may monitor a data source system to collect new data, which may include information about multiple drivers. The computing platform may generate, by inputting the new data into the model, a customized driving output for a first driver, where the customized driving output is based at least in part on information about a second driver. The computing platform may send, to a computing device, the customized driving output and commands directing the computing device to display the customized driving output, which may cause the computing device to display the customized driving output.

Abstract: Methods, computer-readable media, software, and system may generally identify, determine, and understand the significance of commute location data using telematics data. The system and methods may identify significant commute location data and points by analyzing telematics data and capturing GPS locations associated with the mobility of a user. The commute location data may be classified as data points including origin, destination, and waypoints. This commute location data may be used with metadata to identify significant locations associated with the user. The commute location data may also be used with metadata to understand mobility behavior of the user. Lastly, the commute location data may be used with metadata to determine risk associated with the user, such as based on a risk map.

Abstract: Methods, computer-readable media, software, and system may generally build and quantify mobility patterns based on user location data, both at an individual level and an aggregate level. The system may determine the origin and destination data for each trip taken by a user. The system may then define areas of mobility using a mobility graph built from the data. The graph may include nodes and edges. In some examples, the nodes are constructed from the origins and destinations of the trajectories using spatial clustering techniques. Further, the edges between nodes may be constructed based on the trips between them, such as two nodes are connected by an edge if there is at least one trip between them. The edges may be given different weights based on trip frequencies. The system may then determine a region of mobility using the generated mobility graph and data clustering techniques.

Abstract: Methods, computer-readable media, software, and system may generally identify, determine, and understand the significance of commute location data using telematics data. The system and methods may identify significant commute location data and points by analyzing telematics data and capturing GPS locations associated with the mobility of a user. The commute location data may be classified as data points including origin, destination, and waypoints. This commute location data may be used with metadata to identify significant locations associated with the user. The commute location data may also be used with metadata to understand mobility behavior of the user. Lastly, the commute location data may be used with metadata to determine risk associated with the user, such as based on a risk map.

Abstract: Methods, computer-readable media, software, and apparatuses include receiving, from a plurality of risk information sources, risk information associated with a user account, wherein the risk information includes a plurality of risk components, determining, for each of the plurality of risk components, an impact score and a risk probability by applying a machine learning model to risk information associated with the user account, generating an interactive risk index dashboard including a plurality of interactive risk index elements, wherein each of the plurality of interactive risk index elements is associated with a risk component of the plurality of risk components, and displaying, on the display of the apparatus, the interactive risk index dashboard, wherein each of the plurality of interactive risk index elements is displayed in a portion of the interactive risk index dashboard in accordance with a respective determined impact score and risk probability.

Abstract: Methods, computer-readable media, software, and system may generally build and quantify mobility patterns based on user location data, both at an individual level and an aggregate level. The system may determine the origin and destination data for each trip taken by a user. The system may then define areas of mobility using a mobility graph built from the data. The graph may include nodes and edges. In some examples, the nodes are constructed from the origins and destinations of the trajectories using spatial clustering techniques. Further, the edges between nodes may be constructed based on the trips between them, such as two nodes are connected by an edge if there is at least one trip between them. The edges may be given different weights based on trip frequencies. The system may then determine a region of mobility using the generated mobility graph and data clustering techniques.

Abstract: Methods, computer-readable media, software, and system may generally identify, determine, and understand the significance of commute location data using telematics data. The system and methods may identify significant commute location data and points by analyzing telematics data and capturing GPS locations associated with the mobility of a user. The commute location data may be classified as data points including origin, destination, and waypoints. This commute location data may be used with metadata to identify significant locations associated with the user. The commute location data may also be used with metadata to understand mobility behavior of the user. Lastly, the commute location data may be used with metadata to determine risk associated with the user, such as based on a risk map.

Abstract: Methods, computer-readable media, software, and apparatuses include receiving, from a plurality of risk information sources, risk information associated with a user account, wherein the risk information includes a plurality of risk components, determining, for each of the plurality of risk components, an impact score and a risk probability by applying a machine learning model to risk information associated with the user account, generating an interactive risk index dashboard including a plurality of interactive risk index elements, wherein each of the plurality of interactive risk index elements is associated with a risk component of the plurality of risk components, and displaying, on the display of the apparatus, the interactive risk index dashboard, wherein each of the plurality of interactive risk index elements is displayed in a portion of the interactive risk index dashboard in accordance with a respective determined impact score and risk probability.

Abstract: Methods, computer-readable media, software, and apparatuses include receiving, from a plurality of risk information sources, risk information associated with a user account, wherein the risk information includes a plurality of risk components, determining, for each of the plurality of risk components, an impact score and a risk probability by applying a machine learning model to risk information associated with the user account, generating an interactive risk index dashboard including a plurality of interactive risk index elements, wherein each of the plurality of interactive risk index elements is associated with a risk component of the plurality of risk components, and displaying, on the display of the apparatus, the interactive risk index dashboard, wherein each of the plurality of interactive risk index elements is displayed in a portion of the interactive risk index dashboard in accordance with a respective determined impact score and risk probability.

Abstract: Methods, computer-readable media, software, systems and apparatuses may receive, from a user device, notification of a user enrolling in a privacy incident protection application, receive, from the user device, user account information associated with one or more user accounts of the user, where the user account information includes a plurality of contextual settings, determine a risk footprint associated with the user based on the user account information, monitor the one or more user accounts, receive an indication of an incident based on monitoring the one or more user accounts and based on the risk footprint, and transmit an incident notification to a data server provider associated with the incident. The incident notification may include instructions to perform a mitigation action associated with the incident.

Abstract: An apparatus and methods provide trajectory data for a geographic area. Multiple probe data sets are received or identified from one or more mobile devices. The probe data sets include time values in a first sequence associated with location values in the first sequence. At least one of the probe data sets is modified to reverse the location values such that the modified probe data set includes time values in a first sequence associated with location values in a second sequence. A location clustering algorithm is performed on the plurality of probe data sets and the modified probe data set based on the location values.

Abstract: Apparatus and methods are described for identification of a geographic location for sign placement. Probe data is received for a geographic area, and the probe data is collected by one or more sensors. Trips including destinations within the geographic area are matched with road segments from a geographic database. At least one potential sign placement road segment is compared to road segments of the trip. One or more destinations are selected from the trips based on the comparison of the at least one sign placement road segment to the trip road segments.

Abstract: An approach is provided for automatically identifying transportation transition regions (e.g., off-road pickup/drop-off locations) based on probe trajectory data. The approach involves, for example, determining a geographic area that encompasses a point of interest and an associated off-road region. The approach also involves retrieving probe trajectories that intersect the geographic area. The approach further involves segmenting the one or more probe trajectories into a plurality of segments that include on-road and/or off-road segments. The approach also involves processing the plurality of segments to identify one or more transition segments that include a transition involving an on-road segment of the one or more on-road segments or an off-road segment of the one or more off-road segments. The approach further involves clustering one or more probe points of the one or more transition segments to identify the transportation transition region.

Abstract: An approach is provided for detecting stay points from probe data. The approach, for example, involves segmenting a probe trajectory into a first trajectory segment type (e.g., on-road), a second trajectory segment type (e.g., off-road), an unknown trajectory segment type, or a combination thereof. The approach also involves merging the unknown trajectory segment into either the first trajectory segment type or the second trajectory segment type based on a co-occurrence with the unknown trajectory segment. The approach further involves segmenting the first trajectory segment type into first sub-segments and the second trajectory segment type second sub-segments based on a minimum enclosing ball or any other bounding volume with a radius less than or equal to the distance threshold. The approach further involves processing each first sub-segment and each second sub-segment to determine stay points.

Abstract: A method, apparatus and computer program product are provided to facilitate movement of a pedestrian or bicyclist along a route. In the context of a method, routes of one or more autonomous vehicles and of a pedestrian or bicyclist are synchronized. The method includes receiving a route of the pedestrian or bicyclist that extends at least partially along a road network comprised of a plurality of road segments. The method also includes accessing routes to be driven by the one or more autonomous vehicles. The method further includes synchronizing the route of the pedestrians or bicyclists with the route of the one or more autonomous vehicles such that the one or more autonomous vehicles drive alongside the pedestrian or bicyclist while the pedestrian or bicyclist proceeds along with at least a portion of the route.

Abstract: An apparatus and methods provide trajectory data for a geographic area. Multiple probe data sets are received or identified from one or more mobile devices. The probe data sets include time values in a first sequence associated with location values in the first sequence. At least one of the probe data sets is modified to reverse the location values such that the modified probe data set includes time values in a first sequence associated with location values in a second sequence. A location clustering algorithm is performed on the plurality of probe data sets and the modified probe data set based on the location values.

Abstract: An apparatus for providing anonymity in geographic data for probes using a variable mix zone in a geographic region includes a geographic database, a mix zone generator, and a pseudonym generator. The geographic database is configured to store one or more map features in the geographic region. The mix zone generator is configured to define a mix zone boundary having a size based on the one or more map features and monitor probe data for at least one probe. The probe data including a location within a predetermined distance of the mix zone boundary. The pseudonym generator is configured to select a pseudonym for the at least one probe in response to the location of the probe data and apply the pseudonym for the at least one probe in the geographic data when the at least one probe exits the mix zone.

Abstract: An approach is provided for detecting stay points from probe data. The approach, for example, involves segmenting a probe trajectory into a first trajectory segment type (e.g., on-road), a second trajectory segment type (e.g., off-road), an unknown trajectory segment type, or a combination thereof. The approach also involves merging the unknown trajectory segment into either the first trajectory segment type or the second trajectory segment type based on a co-occurrence with the unknown trajectory segment. The approach further involves segmenting the first trajectory segment type into first sub-segments and the second trajectory segment type second sub-segments based on a minimum enclosing ball or any other bounding volume with a radius less than or equal to the distance threshold. The approach further involves processing each first sub-segment and each second sub-segment to determine stay points.