Weather-driven multi-category infrastructure impact forecasting

Patent metadata

Field	Value
Publication number	US-9536214-B2
Application number	US-201615075603-A
Country	US
Kind code	B2
Filing date	Mar 21, 2016
Priority date	Apr 14, 2015
Publication date	Jan 3, 2017
Grant date	Jan 3, 2017

Abstract

A method, system, and computer program product for resource management are described. The method includes selecting trouble regions within the service area, generating clustered regions, and training a trouble forecast model for the trouble regions for each type of damage, the training for each trouble region using training data from every trouble region within the clustered region associated with the trouble region. The method also includes applying the trouble forecast model for each trouble region within the service area for each type of damage, determining a trouble forecast for the service area for each type of damage based on the trouble forecast for each of the trouble regions within the service area, and determining a job forecast for the service area based on the trouble forecast for the service area, wherein the managing resources is based on the job forecast for the service area.

First claim

What is claimed is:

1. A computer implemented method of managing resources based on weather-related damage in a service area, the method comprising:
selecting, by a processor, trouble regions within the service area;
generating clustered regions, each of the clustered regions including at least one of the trouble regions within the service area and each of the trouble regions within the service area being associated with one of the clustered regions;
training a trouble forecast model for each of the trouble regions for each type of the weather-related damage, the training for each of the trouble regions using training data from every one of the trouble regions within the clustered region associated with the trouble region, wherein the training data from each of the trouble regions within the clustered region is multiplied by a different scaling factor;
applying the trouble forecast model for each of the trouble regions within the service area for each type of the weather-related damage to obtain a trouble forecast for each of the trouble regions within the service area for each type of the weather-related damage;
determining a trouble forecast for the service area for each type of the weather-related damage based on the trouble forecast for each of the trouble regions within the service area; and
determining a job forecast for the service area based on the trouble forecast for the service area according to a trouble-to-job mapping, wherein the managing resources is based on the job forecast for the service area, the applying the trouble forecast model for each of the trouble regions includes spatially interpolating weather forecast information within the respective trouble region to a centroid of the respective trouble region to obtain interpolated data and computing scoring input features from the interpolated data that are used to determine the trouble forecast for the respective trouble region.

Assignees

• IBM

Inventors

• Heng Fook-Luen
• Li Zhiguo
• Siegel Stuart A
• Singhee Amith
• Wang Haijing

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06Q10/06315 Primary

  Needs-based resource requirements planning or analysis · CPC title

• G06N99/005

  Physics · mapped topic

• G01W1/10 Primary

  Devices for predicting weather conditions (computers per se G06; display devices G09) · CPC title