Verizon Connect Ireland Limited

Verizon Connect Development Limited

Verizon Patent and Licensing Inc.

Verizon Connect Telo Inc.

Alessandro Lori

Francesco Sambo

Leonardo Taccari

Luca Bravi

Samuele Salti

Matteo Simoncini

Leonardo Sarti

Peter Mitchell

Fabio Schoen

Jason Mathew Koch

Aurel Pjetri

Stefano Caprasecca

Tommaso Bianconcini

Andrea Benericetti

David Di Lorenzo

John Molamphy

Andrew Harbourne-Thomas

Wan Luo

Yaoyang Qian

A device may receive vehicle operation data associated with operation of a plurality of vehicles, and may process the vehicle operation data to generate processed vehicle operation data. The device may extract multiple features from the processed vehicle operation data, and may train machine learning models, with the multiple features, to generate trained machine learning models that provide model outputs. The device may process the multiple features, with a feature selection model and based on the model outputs, to select sets of features from the plurality of features, and may process the sets of features, with the trained machine learning models, to generate indications of driving behavior and reliabilities of the indications. The device may select a set of features, from the sets of features, based on the indications and the reliabilities, where the set of features may be calculated by a device associated with a particular vehicle.

Systems and methods for utilizing machine learning and feature selection to classify driving behavior

A method and system for identifying recurrent stops of a vehicle fleet having a plurality of vehicles. The method comprises retrieving historical GPS tracks of the vehicle fleet over a period of time; detecting stops made by the vehicle fleet along travelled routes that are associated with the historical GPS tracks; constructing a coverage area that covers the travelled routes; discretizing the coverage area into a plurality of cells; determining whether a cell is a recurrent stop based on a fleet stay period associated with that cell; and classifying a determined recurrent stop into a plurality of categories.

System and method for detecting and classifying recurrent stops of a vehicle fleet

A method and system for classifying a vehicle based on low frequency GPS tracks. The method and system comprise retrieving a low frequency GPS track having a sampling interval of at least 20 seconds; deriving additional data from the low frequency GPS track, the additional data including interval speed and instantaneous acceleration of the vehicle; extracting a plurality of data sets from the low frequency GPS track and the additional data; generating a plurality of features from the extracted data sets; and providing the plurality of generated features to a classifier that classifies the vehicle into a predetermined class.

System and method for determining a vehicle classification from GPS tracks

A device receives location information and work order information associated with multiple vehicles, and groups the location information into engine off information, idling information, and journey information. The device combines, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles, and matches corresponding work order information with the vehicle stop information to generate matched information. The device extracts stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information, and utilizes the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the multiple vehicles. The device provides information associated with the work order stops and the non-work order stops for the multiple vehicles.

Stop purpose classification for vehicle fleets

A system and method for optimizing traveled routes of a fleet. The method comprises reconstructing routes traveled by vehicles of the fleet based on historical GPS traces of the fleet; determining stops made by the vehicles along the traveled routes; and classifying the stops into work stops and non-work stops; and optimizing routes for the work stops.

System and method for deriving operation information of a fleet and analyzing the same

A device can obtain acceleration data and GPS location data. The GPS location data can include a plurality of GPS location data samples relating to vehicles. The acceleration data can include a plurality of acceleration data samples relating to one or more of the vehicles. The device can determine, using the plurality of acceleration data samples or the plurality of GPS location data samples, a potential wrong-way travel event associated with a vehicle, determine whether the vehicle is associated with an industry in which vehicles legitimately engage in wrong-way travel after determining the potential wrong-way travel event, and perform one or more actions to cause information regarding the potential wrong-way travel event to be provided to a user device based on determining the potential wrong-way travel event and determining whether the vehicle is associated with an industry in which vehicles legitimately engage in wrong-way travel.

Identifying wrong-way travel events

A device can receive message data associated with a vehicle tracking unit (VTU). The device can identify, based on the message data, the VTU as an inactive VTU. The device can compute a feature vector, associated with the VTU, based on the message data and on environmental data associated with the VTU. The feature vector can be computed based on identifying the VTU as an inactive VTU. The device can determine, using an inactivity classification model, an inactivity classification associated with the VTU. The inactivity classification can be determined based on providing the feature vector, associated with the VTU, as an input to the inactivity classification model. The device can cause an inactivity action to be performed based on the inactivity classification.

Automatic classification of inactive vehicle tracking unit

A video classification platform receives a first message that includes a link to video data including video frames captured by one or more cameras associated with the vehicle, and including information concerning a vehicle and a driving event. The platform obtains the video data using the link, identifies the vehicle and the driving event based on the information, and determines objects in a video frame. The platform constructs a collision cone of the vehicle for the video frame and determines, based on the collision cone, a set of objects that have a potential to collide with the vehicle. The platform assigns a category to the driving event based on the set of objects, the collision cone of the vehicle, and the information, generates a second message that includes the category and the information, and sends the second message to a client device to display the second message.

Automatic collection and classification of harsh driving events in dashcam videos

A device can receive GPS data or values for a set of metrics at a set of GPS points that form a GPS track of a vehicle. The device can determine additional values for additional metrics using the GPS data or the values for the set of metrics. The device can determine a set of vectors for the set of GPS points using the GPS data, the values, or the additional values. The set of vectors can be used in a recurrent neural network (RNN) to classify the vehicle. The device can process the set of vectors via one or more sets of RNN layers of the RNN. The device can determine a classification of the vehicle using a result of processing the set of vectors. The result can be output by the output layer. The device can perform an action based on the classification of the vehicle.

Vehicle classification using a recurrent neural network (RNN)

A method for finding an approximation to the all-pairs shortest travel path between a number of predetermined nodes, comprising clustering nodes of an original road network into a plurality of subgroups so that the number of nodes in each subgroup is no greater than a first predetermined threshold and the maximum distance between any two nodes of a subgroup is no greater than a second predetermined threshold; adding information of intra group shortest paths for all pairs in a same subgroup to a newly created higher level road network; adding information of inter group shortest paths for the plurality of subgroups to the same road network; and searching the same road network for the shortest travel path. In those cases in which the path returned is not exact, the path represents one in the original map, even if not necessarily the best one.

Growing community of inventors

Florence, Italy

Alessandro Lori