US 11,598,900 B2Granted

Weather-driven multi-category infrastructure impact forecasting

AssigneeUtopus Insights, Inc.

InventorsFook-Luen Heng, Zhiguo Li, Stuart A. Siegel, Amith Singhee, Haijing Wang

Life of this patent

Estimating the term…

Loading patent…

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.

Claims18

Dependent claims

A non-transitory computer program product, the non-transitory computer program product comprising a computer readable storage medium having instructions embodied therewith, the instructions executable by at least one processor to perform a method comprising:

selecting a plurality of trouble regions within a 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, the at least one of the trouble region of each cluster region being generated based on a distance between the at least one of the trouble region and other trouble regions of the plurality of trouble regions within the service area;
for each of the trouble regions:
training a plurality of trouble forecast models for each type of weather-related damage, each of the plurality of trouble forecast model being for a different type of weather-related damage, the training for each of the plurality of trouble forecast models including:
receiving historical weather data from a plurality of weather data sources, the historical weather data being from at least a portion of the service area including a particular trouble region;
filtering out low confidence historical weather data with data quality filters, each of the quality filters being specific to one of the plurality of weather data sources;
and
normalizing the historical weather data for a particular weather-related damage to a common repeating time interval to obtain a normalized time series for a particular weather feature, the normalized being based on one of a minimum, maximum, an average, or a rate of change;
and
applying each of the trouble forecast models for the at least one clustered region within the service area to obtain a trouble forecast for the particular trouble region within the service area for each type of the weather-related damage;
determining a regional forecast for a geographic service area based on the trouble forecast for the geographic service area in order to facilitate management of resources by relocating equipment and personnel within the service area;
and
providing the regional forecast for the geographic service area based on the trouble forecast, in order to minimize an impact of the trouble forecast.

10 more elements

A system for managing resources based on weather-related damage in a service area, the system comprising:

at least one processor;
and
memory including instructions executable by the at least one processor to configure the at least one processor to:
selecting a plurality of trouble regions within a 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, the at least one of the trouble region of each cluster region being generated based on a distance between the at least one of the trouble region and other trouble regions of the plurality of trouble regions within the service area;
for each of the trouble regions:
training a plurality of trouble forecast models for each type of weather-related damage, each of the plurality of trouble forecast model being for a different type of weather-related damage, the training for each of the plurality of trouble forecast models including:
receiving historical weather data from a plurality of weather data sources, the historical weather data being from at least a portion of the service area including a particular trouble region;
filtering out low confidence historical weather data with data quality filters, each of the quality filters being specific to one of the plurality of weather data sources;
and
normalizing the historical weather data for a particular weather-related damage to a common repeating time interval to obtain a normalized time series for a particular weather feature, the normalized being based on one of a minimum, maximum, an average, or a rate of change;
and
applying each of the trouble forecast models for the at least one clustered region within the service area to obtain a trouble forecast for the particular trouble region within the service area for each type of the weather-related damage;
determining a regional forecast for a geographic service area based on the trouble forecast for the geographic service area in order to facilitate management of resources by relocating equipment and personnel within the service area;
and
providing the regional forecast for the geographic service area based on the trouble forecast, in order to minimize an impact of the trouble forecast.

13 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/224,116Filed 6 Apr 2021 · continuation
Priority: 14 Apr 2015
Published: US 2021/0223434 A122 Jul 2021
Granted: 7 Mar 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G01W 1/10
Meteorology: devices for predicting weather conditions
G06N 5/04
Computing arrangements using knowledge-based models: inference or reasoning models
G06N 7/01
Computing arrangements based on specific mathematical models: probabilistic graphical models, e.g. probabilistic networks
G06N 20/00
Machine learning

Family

Application62/147,003Us provisional application · filed 14 Apr 2015
Application15/002,494Parent of this continuation · filed 21 Jan 2016
Application15/075,603Parent of this continuation · filed 21 Mar 2016
Application15/287,846Parent of this continuation · filed 7 Oct 2016
US 9,536,214 B2Parent of this continuation · filed 3 Jan 2017
Application16/546,268Parent of this continuation · filed 20 Aug 2019
US 10,387,802 B2Parent of this continuation · filed 20 Aug 2019
US 2021/0223434 A1Pre-grant publication · published 22 Jul 2021
US 11,048,021 B2Parent of this continuation
US 10,989,838 B2Parent of this continuation
US 2016/0306075 A1Published application
US 2016/0307138 A1Published application
US 2017/0017904 A1Published application
US 2020/0111020 A1Published application
US 11,598,900 B2This patent

From the US filing history. Foreign family members aren’t listed.