Data mining for alerts regarding road conditions

Patent metadata

Field	Value
Publication number	US-10319229-B1
Application number	US-201815887282-A
Country	US
Kind code	B1
Filing date	Feb 2, 2018
Priority date	Feb 2, 2018
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

Embodiments of the invention are directed to methods and systems for forecasting hazardous road conditions. The method includes determining a plurality of sections of road to analyze and correlating the sections of roads to localized weather forecasts. The method also includes performing a road surface condition analysis for each section of road of the plurality of sections of road and based on a prediction of a hazardous road condition, generating an alert regarding the hazardous road condition.

First claim

What is claimed is:

1. A computer-implemented method for forecasting hazardous road conditions, the method comprising:
determining a plurality of sections of road to analyze, wherein the plurality of sections of road are a subset of a road network and wherein the plurality of sections are determined to be inherently dangerous based on an analysis of accident data obtained from police departments and insurance company databases;
correlating each of the plurality of sections of roads to localized weather forecasts;
performing a road surface condition analysis for each section of road of the plurality of sections of roads to generate a prediction of a hazardous road condition; and
based on the prediction of the hazardous road condition, generating an alert regarding the hazardous road condition.

2. The computer-implemented method of claim 1 , wherein:
the hazardous road condition comprises a section of road with accumulated snow, ice, rain, or ground fog.

3. The computer-implemented method of claim 2 , wherein:
performing the road surface condition analysis comprises performing a Fast All-Season Solid State (FASST) model based on the localized weather forecasts to find the hazardous road condition.

4. The computer-implemented method of claim 2 , further comprising:
gathering road data regarding each section of road; and wherein:
the road surface condition analysis uses road data to find the hazardous road condition; and
the road data comprises material of the section of road, presence of bridges, and slope.

5. The computer-implemented method of claim 2 , wherein:
the road surface condition analysis further uses astronomical data, soil type, aspect angle, and a presence of shade as inputs.

6. The computer-implemented method of claim 1 , wherein:
the alert is sent to a centralized location for dissemination.

7. The computer-implemented method of claim 1 , wherein:
the alert is pushed to mobile electronic devices.

8. A computer system for forecasting hazardous road conditions, the computer system comprising:
a memory; and
a processor system communicatively coupled to the memory;
the processor system configured to perform a method comprising:
determining a plurality of sections of road to analyze, wherein the plurality of sections of road are a subset of a road network and wherein the plurality of sections are determined to be inherently dangerous based on an analysis of accident data obtained from police departments and insurance company databases;
correlating each of the plurality of sections of roads to localized weather forecasts;
performing a road surface condition analysis for each section of road of the plurality of sections of road to generate a prediction of a hazardous road condition; and
based on the prediction of the hazardous road condition, generating an alert regarding the hazardous road condition.

9. The computer system of claim 8 , wherein:
the hazardous road condition comprises a section of road with accumulated snow, ice, rain, or ground fog.

10. The computer system of claim 9 , wherein:
performing the road surface condition analysis comprises performing a Fast All-Season Solid State (FASST) model based on the localized weather forecasts to find the hazardous road condition.

11. The computer system of claim 10 , wherein:
the road surface condition analysis further uses astronomical data, soil type, aspect angle, and a presence of shade as inputs.

12. The computer system of claim 9 , wherein the processor system is further configured to:
gather road data regarding each section of road; and wherein:
the road surface condition analysis uses road data to find the hazardous road condition; and
the road data comprises material of the section of road, presence of bridges, and slope.

13. The computer system of claim 8 , wherein:
the alert is sent to a centralized location for dissemination.

14. The computer system of claim 8 , wherein:
the alert is pushed to mobile electronic devices.

Assignees

• IBM

Inventors

• Dow Eli M
• Watson Campbell D
• Auger Guillaume
• Henderson Michael E

Classifications

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G08G1/0967 Primary

  Systems involving transmission of highway information, e.g. weather, speed limits (transmission of navigation instructions to the vehicle G08G1/0968) · CPC title

• G08G1/012 Primary

  from other sources than vehicle or roadside beacons, e.g. mobile networks · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title

• G08G1/096741

  where the source of the transmitted information selects which information to transmit to each vehicle · CPC title