Abstract: A route scheduling system for a vehicle or fleet of vehicles can recalculate a scheduled route based on input received after the formulation and/or dispatch of the initial route. The additional inputs can be used for recalculation and changes in route selection, which may include a variety of inputs, such as weather conditions, traffic conditions, customer needs, vehicle inventory, and emergency situations. The recalculation of the routes can allow for route selection to be performed in real-time in order for fleets and vehicles to optimize the allocation of resources.

Abstract: The present invention provides a technique for building natural language parsers by implementing a country and/or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.

Abstract: Vehicle management systems and associated processes can incorporate calculations for categorizing locations on a map as within one or more territories based on proximity of the location to predetermined points with in the territories. The systems and processes can also incorporate techniques for estimating total distance required to traverse a route reaching all of a set of predetermined stops, without using a routing algorithm that would provide a usable route for a vehicle, but is less computationally demanding. The systems and processes can also include techniques for incorporating legs of a route that extend through a temporary exclusion zone.

Abstract: The present invention provides a technique for building natural language parsers by implementing a country and/or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.

Abstract: The present invention provides a technique for building natural language parsers by implementing a country and/or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.

Abstract: A route scheduling system for a vehicle or fleet of vehicles can recalculate a scheduled route based on input received after the formulation and/or dispatch of the initial route. The additional inputs can be used for recalculation and changes in route selection, which may include a variety of inputs, such as weather conditions, traffic conditions, customer needs, vehicle inventory, and emergency situations. The recalculation of the routes can allow for route selection to be performed in real-time in order for fleets and vehicles to optimize the allocation of resources.

Abstract: The present invention provides a technique for building natural language parsers by implementing a country and/or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.