Detecting and mitigating risk in a transport network

Patent metadata

Field	Value
Publication number	US-11665184-B2
Application number	US-201916250632-A
Country	US
Kind code	B2
Filing date	Jan 17, 2019
Priority date	Jan 17, 2019
Publication date	May 30, 2023
Grant date	May 30, 2023

Abstract

Embodiments for implementing intelligent risk detection and mitigation in a transport network by a processor. Data gathered from a plurality of data sources relating to an entity and a selected region of interest may be analyzed. Behavior of an entity, in relation to a risk event, may be learned and interpreted based on a plurality of identified contextual factors, geographical data, current data, historical data, a learned risk event model, or a combination thereof. One or more mitigation actions may be performed to mitigate risk of occurrence or a possible negative impact of the risk event caused at least in part by the behavior of the entity.

First claim

The invention claimed is:

1. A method for implementing intelligent risk detection and mitigation in a transport network by a processor, comprising:
learning and interpreting behavior of a vehicle in relation to a risk event indicative of bodily harm based on information representing a plurality of identified contextual factors, geographical data, current data, historical data, and a learned risk event model, wherein learning and interpreting the behavior includes identifying, based on the information inclusive of a trajectory and speed of the vehicle, that the vehicle is suspiciously traveling to one or more sensitive locations not permitting of vehicular traffic and known to attract a density of pedestrians within an identified risk area of a selected region based on at least user device data of the pedestrians within the identified risk area; and
performing one or more mitigation actions to mitigate risk of occurrence or a possible negative impact of the risk event caused at least in part by the behavior of the vehicle, wherein the one or more mitigation actions include remotely disabling the vehicle by an entity external to the vehicle.

2. The method of claim 1 , further including analyzing data gathered from a plurality of data sources relating to the behavior and the selected region.

3. The method of claim 1 , further including identifying the one or more sensitive locations within the selected region having a level of risk of occurrence of the risk event greater than a defined risk threshold.

4. The method of claim 1 , further including:
detecting a level of risk of occurrence of the risk event in the selected region according to the behavior; or
alerting one or more user equipment (UE) of a plurality of users upon the level of risk of occurrence of the risk event being greater than a defined risk threshold.

5. The method of claim 1 , further including providing a list of entities identified as having behavior having a level of risk of causing the risk event greater than a defined risk threshold.

6. The method of claim 1 , further including learning a sensitivity map from the plurality of identified contextual factors, the geographical data, the current data, the historical data, the learned risk event model, or a combination thereof.

7. The method of claim 1 , further including initializing a machine learning mechanism to:
collecting data gathered from one of a plurality of internet of things (IoT) devices and data sources relating to the behavior and the selected region;
learning and defining a level of risk of occurrence of the risk event in the selected region according to the behavior based on analysis of the collected data;
using feedback information to learn behavior of the vehicle and one or more mitigating actions;
monitoring and determining a presence or absence of a risk of occurrence of the risk event for the selected region according to the behavior of the vehicle.

8. A system for implementing intelligent risk detection and mitigation in a transport network, comprising:
a hardware processor;
a hardware memory having executable instructions stored therein, wherein the executable instructions, when executed, cause the hardware processor to:
learn and interpret behavior of a vehicle in relation to a risk event indicative of bodily harm based on information representing a plurality of identified contextual factors, geographical data, current data, historical data, and a learned risk event model, wherein learning and interpreting the behavior includes identifying, based on the information inclusive of a trajectory and speed of the vehicle, that the vehicle is suspiciously traveling to one or more sensitive locations not permitting of vehicular traffic and known to attract a density of pedestrians within an identified risk area of a selected region based on at least user device data of the pedestrians within the identified risk area; and
perform one or more mitigation actions to mitigate risk of occurrence or a possible negative impact of the risk event caused at least in part by the behavior of the vehicle, wherein the one or more mitigation actions include remotely disabling the vehicle by an entity external to the vehicle.

9. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to analyze data gathered from a plurality of data sources relating to the behavior and the selected region.

10. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to identify the one or more sensitive locations within the selected region having a level of risk of occurrence of the risk event greater than a defined risk threshold.

11. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to:
detect a level of risk of occurrence of the risk event in the selected region according to the behavior; or
alert one or more user equipment (UE) of a plurality of users upon the level of risk of occurrence of the risk event being greater than a defined risk threshold.

12. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to provide a list of entities identified as having behavior having a level of risk of causing the risk event greater than a defined risk threshold.

13. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to learn a sensitivity map from the plurality of identified contextual factors, the geographical data, the current data, the historical data, the learned risk event model, or a combination thereof.

14. The system of claim 8 , wherein the executable instructions, when executed by the hardware processor, further cause the hardware processor to initialize a machine learning mechanism to:
collect data gathered from one of a plurality of internet of things (IoT) devices and data sources relating to the behavior and the selected region;
learn and define a level of risk of occurrence of the risk event in the selected region according to the behavior based on analysis of the collected data;
use feedback information to learn behavior of the vehicle and one or more mitigating actions; and
monitor and determine a presence or absence of a risk of occurrence of the risk event for the selected region according to the behavior of the vehicle.

15. A computer program product for, by a processor, implementing intelligent risk detection and mitigation in a transport network, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that learns and interprets behavior of a vehicle in relation to a risk event indicative of bodily harm based on information representing a plurality of identified contextual factors, geographical data, current data, historical data, and a learned risk event model, wherein learning and interpreting the behavior includes identifying, based on the information inclusive of a trajectory and speed of the vehicle, that the vehicle is suspiciously traveling to one or more sensitive locations not permitting of vehicular traffic and known to attract a density of pedestrians within an identified risk area of a selected region based on at least user device data of the pedestrians within the identified risk area; and

Assignees

• IBM

Inventors

• Monteil Julien
• LASSOUED Yassine
• Mevissen Martin
• Dekusar Anton
• Zhuk Sergiy
• Ordonez-Hurtado Rodrigo
• Shorten Robert
• Griggs Wynita

Classifications

• H04L41/0895

  Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements · CPC title

• H04L41/40

  using virtualisation of network functions or resources, e.g. SDN or NFV entities · CPC title

• H04L63/1425 Primary

  Traffic logging, e.g. anomaly detection · CPC title

• H04L41/0806 Primary

  for initial configuration or provisioning, e.g. plug-and-play · CPC title

• G06N5/025

  Extracting rules from data · CPC title