US-12620043-B1 - Computer-based system to determine a distribution of times a vehicle spends at different locations on a route

Abstract

A computer-based system to determine a distribution of times a vehicle spends at different locations on a route has a global positioning system, a microprocessor, an output device and computer instructions. The instructions cause the system to read in from the GPS a monitored location of the vehicle and an associated time. The system then calculates a corrected location of the vehicle based on the closest point of the route to the monitored location. The system then computes the distribution of the times the vehicle spends at different locations on said route based at least in part on the corrected location and associated time. The system then outputs the distribution on a computer screen.

Inventors

• Justin N. Smith
• Sean Hughes
• James Shasta Daulton

Assignees

• Applied Underwriters, Inc.

Dates

Publication Date

20260505

Application Date

20190923

Claims (5)

1. 1 . A system for modifying waiting times a vehicle spends at different locations on a route, the system comprising: a vehicle comprising a location measurement computer comprising a memory, a processor, and a plurality of computer code, the code stored in the memory, the code when executed by the processor causes the processor to: iteratively receive, from a global positioning system (GPS), a plurality of monitored locations over a period of time, wherein the monitored locations are subject to errors when one or more of the GPS satellites are partially or completely blocked by buildings leading to GPS signal blockage resulting in errors in monitored position, each monitored location associated with a time, the plurality of monitored locations comprised within a pre-defined route, the plurality of monitored locations associated to the vehicle; receive, from a database, a plurality of constraints associated to the vehicle, wherein the constraints comprise track locations for the vehicle on a track; calculate a plurality of corrected locations to at least partially correct for the errors in monitored position, each corrected location of the plurality of corrected locations equal to a position, of a plurality of positions, on the pre-defined route, each position, of the plurality of positions, being closest to an associated monitored location, each corrected location based on at least one constraint of the plurality of constraints wherein if a monitored location is off of the track, the corrected location is set to the nearest track location; wherein to calculate the corrected location, the code when further executed by the processor causes the processor to: examine a set of track locations for each monitored location received from the GPS; determine a distance between the monitored location and each track location in the set using a norm function; and select, as the corrected location, the track location that minimizes the distance to the monitored location; and further apply a velocity-bound constraint comparing a velocity implied by the corrected location to a velocity derived from at least one prior corrected location, and reject or adjust the corrected location when the implied velocity exceeds a predetermined bound; calculate a plurality of durations, each duration associated with a quantity of time the vehicle spends at each corrected location of the plurality of corrected locations; for each corrected location, of the plurality of corrected locations: compute a level of risk of physical damage to the vehicle on the route by: receiving risk data comprising a plurality of risk locations, each risk location having an associated risk amplitude and an associated risk radius; for each risk location of the plurality of risk locations: determining a risk distribution around the risk location based on the associated risk amplitude and risk radius; calculating a risk value at the corrected location based on distance from each risk location; and summing the risk values from all risk locations to determine the level of risk of physical damage at the corrected location; modify at least one waiting time of the vehicle on the route by shifting a waiting position of the vehicle to a location having a lower calculated risk of physical damage; and output the risk values and the modified at least one waiting time to an output device.
2. 2 . The system of claim 1 wherein the distribution is presented on the output device at least in part by an amplitude and a radius.
3. 3 . The system of claim 1 wherein the route is a three-dimensional route.
4. 4 . The system of claim 1 wherein the vehicle is one or more of: a) an automobile; or b) the vehicle on a track.
5. 5 . The system of claim 1 wherein the output device is a computer screen and the output comprises one or more of: a) a bar graph; or b) a map.

Description

COPYRIGHT AND TRADEMARK NOTICE A portion of the disclosure of this patent document contains material to which a claim for copyright is made. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent file or records, but reserves all other copyright rights whatsoever. FIELD OF THE INVENTION Embodiments of the present invention relate to artificial intelligence means for forecasting terror risk. BACKGROUND OF THE INVENTION Terrorist risks are difficult to predict. There is very little data available on actual attacks. Thus, most of the work in this area has involved the creation of so-called “Delphic” models, which are produced by creating a group of acknowledged experts on terrorism and having them produce a “catalog” of likely attacks, including details as to method, location, intensity, and timing. Several such inventories have been produced by specialist catastrophe risk modeling firms and are in use. Most of the details are not in the public domain, but certain included locations and events are known, as is the overall size of a typical catalog, which includes about 250,000 possible events. Employers have used these catalogs to estimate the level of terror an employee faces by looking at the terror risk of said employee's address of employment. Unfortunately, this method does not take into account the risks employees face when they work away from their formal address of employment. Thus there is a need for a computer-based prediction system for forecasting the level of risk an employee faces that takes into account the location distribution of said employee in the course of said employee's work. SUMMARY OF THE INVENTION The summary of the invention is provided as a guide to understanding the invention. It does not necessarily describe the most generic embodiment of the invention or the broadest range of alternative embodiments. FIG. 1 illustrates a computer-based prediction system 100 for forecasting the level of risk an employee faces from a terrorist event that takes into account said employee's location distribution. As used herein, a “computer-based system” comprises an input device for receiving data, an output device for outputting data in tangible form (e.g. printing or displaying on a computer screen), a permanent memory for storing data and computer code, and a microprocessor for executing computer code wherein said computer code resident in said permanent memory will physically cause said microprocessor to read-in data via said input device, process said data within said microprocessor to produce output data and output said output data via said output device. Within FIG. 1, boxes represent modules and bidirectional arrows indicate data transmission. A module represents at least a portion of a computer-based system capable of carrying out a particular task. Modules may represent physically separate systems or unitary systems. Multiple modules may be executed by the same system. The prediction system comprises an employee risk module 110. Said employee risk module reads employee location distribution data 102 from an employee location database 104. An employee location distribution is a set of data describing the physical location of an employee during the course of a work period. At a minimum, an employee location distribution comprises a first location and a first amount of time spent at said first location and a second location and a second amount of time spent at said second location. The employee risk module also reads in terror risk distribution data 106 from a terror risk database 108. A terror risk distribution comprises data suitable for calculating a probability of terror attack of a given threshold of severity for one or more of said locations of said employee location distribution. The employee risk module then calculates the level of risk an employee faces from a terrorist event according to the equation: EmployeeRisk=∑x,y,tEmployeeLocationx,y,t*⁢TerrorRiskx,y,t where: a) EmployeeRisk is a level of risk an employee faces from a terrorist event;b) x, y indicates an employee location;c) t indicates a time which said employee is at said employee location;d) EmployeeLocationx,y,t is a distribution of said employee location expressed as a relative time spent by said employee at each location x, y at time t; ande) TerrorRiskx,y,t is the value of a distribution of terror risk at x, y, t expressed as a relative probability of a terror event at each of said employee locations x, y at time t. Thus if an employee spent 80% of their time at a first location where the relative probability of a terror event was 1, and 20% of their time at a second location where the relative probability of a terror event was 10, then the EmployeeRisk for said employee would be 2.8. The level of terror risk can then be output 114 to a user 116 via an output device so that said user can determ