Abstract: Methods, systems, and computer programs are presented for the management of lane-departure (LD) events. One method includes training a classifier for LD events and loading the classifier into a vehicle. LD events are detected based on outward images using the classifier, while the turn signal is monitored to prevent false triggers. If an LD event is detected, rules are checked for alerting the driver and deciding whether to alert the driver or not. Subsequently, additional rules are checked for reporting the event and deciding whether to report the event to a Behavior Monitoring System (BMS) or to discard it. The method also includes a solid line departure model that identifies crossing dashed, solid-white, and solid-yellow lanes, delaying alerts and event generation until a significant portion of the vehicle crosses over the lane. The model also outputs a confidence score reflecting the amount of vehicle deviation from the driving lane.

Abstract: A quick action menu system may be configured to perform operations that include: causing display of a graphical user interface (GUI) at a client device, the GUI comprising a display of a persistent icon at a position within the GUI; receiving a selection of the persistent icon from the client device; accessing user profile data associated with a user of the client device responsive to the input that selects the persistent icon; and causing display of a quick actions menu to display content associated with the user profile data.

Abstract: A quick action menu system may be configured to perform operations that include: causing display of a graphical user interface (GUI) at a client device, the GUI comprising a display of a persistent icon at a position within the GUI; receiving a selection of the persistent icon from the client device; accessing user profile data associated with a user of the client device responsive to the input that selects the persistent icon; and causing display of a quick actions menu to display content associated with the user profile data.

Abstract: It may be desired to query a large record of events to retrieve certain segments of the data that provide information of interest. However, the data might not be structured such that it is conducive to generate/execute queries that inquire about net changes of events over time. Query language may also be interpreted differently by different analysts. In some embodiments data related to events is assembled into a data structure having a format logically equivalent to a double entry transition table. Each event may have two entries in the table: a first entry representing the event as a transition from a previous state to a current state, and a second entry representing the reverse transition of the first entry. In some embodiments, a query executor tool may be provided as a graphical user interface for entering information of interest to be queried.