Estimating incident duration
First Claim
1. A method for incident duration prediction carried out by a computing device via a computer-aided dispatch system module, a traffic measurement detector system module, a spatial-temporal module, and a regression model module, wherein the method comprises:
- obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
obtaining traffic data in real-time for the selected geographic area from a system of one or more traffic measurement detectors;
spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, wherein said spatially and temporally associating is carried out by the spatial-temporal module executing on the computing device; and
predicting incident duration of at least one additional traffic-related incident using one or more regression models, wherein said predicting is based on the incident duration data for the at least one traffic-related incident and incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one additional traffic-related incident via implementing a hybrid predictive model that combines an algorithm for recursive partitioning based on at least one permutation test with a quantile regression model by employing a regression tree wherein a regression model is fitted to each final node of the tree to provide predicted values of incident duration, and wherein said predicting is carried out by the regression model module executing on the computing device.
1 Assignment
0 Petitions
Accused Products
Abstract
A method, an apparatus and an article of manufacture for incident duration prediction. The method includes obtaining incident data for at least one traffic-related incident in a selected geographic area, obtaining traffic data for the selected geographic area, spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, and predicting incident duration of at least one additional traffic-related incident based on the incident duration data for the at least one traffic-related incident.
15 Citations
20 Claims
-
1. A method for incident duration prediction carried out by a computing device via a computer-aided dispatch system module, a traffic measurement detector system module, a spatial-temporal module, and a regression model module, wherein the method comprises:
- obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
obtaining traffic data in real-time for the selected geographic area from a system of one or more traffic measurement detectors;
spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, wherein said spatially and temporally associating is carried out by the spatial-temporal module executing on the computing device; and
predicting incident duration of at least one additional traffic-related incident using one or more regression models, wherein said predicting is based on the incident duration data for the at least one traffic-related incident and incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one additional traffic-related incident via implementing a hybrid predictive model that combines an algorithm for recursive partitioning based on at least one permutation test with a quantile regression model by employing a regression tree wherein a regression model is fitted to each final node of the tree to provide predicted values of incident duration, and wherein said predicting is carried out by the regression model module executing on the computing device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15)
- obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
-
16. A method for incident duration prediction carried out by a computing device via a computer-aided dispatch system module, and a regression model module, wherein the method comprises:
- obtaining incident data for at least one traffic-related incident, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, and wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
predicting incident duration of at least one additional traffic-related incident based on the incident data for the at least one traffic-related incident and incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one additional traffic-related incident by implementing a predictive model that combines an algorithm for recursive partitioning based on at least one permutation test with a quantile regression model by employing a regression tree wherein a regression model is fitted to each final node of the tree to provide predicted values of incident duration, and wherein said predicting is carried out by the regression model module executing on the computing device; and
calibrating the quantile regression model without traffic data to predict the incident duration of the at least one additional traffic-related incident without traffic data, wherein said calibrating is carried out by the regression model module executing on the computing device.
- obtaining incident data for at least one traffic-related incident, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, and wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
-
17. An article of manufacture comprising a computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computing device to carry out a plurality of method steps via a computer-aided dispatch system module, a traffic measurement detector system module, a spatial-temporal module, and a regression model module, said plurality of method steps comprising:
- obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
obtaining traffic data in real-time for the selected geographic area from a system of one or more traffic measurement detectors;
spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, wherein said spatially and temporally associating is carried out by the spatial-temporal module executing on the computing device; and
predicting incident duration of at least one additional traffic-related incident using one or more regression models, wherein said predicting is based on the incident duration data for the at least one traffic-related incident and incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one additional traffic-related incident via implementing a hybrid predictive model that combines an algorithm for recursive partitioning based on at least one permutation test with a quantile regression model by employing a regression tree wherein a regression model is fitted to each final node of the tree to provide predicted values of incident duration, and wherein said predicting is carried out by the regression model module executing on the computing device. - View Dependent Claims (18)
- obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
-
19. A system for incident duration prediction carried out by a computing device via a computer-aided dispatch system module, a traffic measurement detector system module, a spatial-temporal module, and a regression model module, comprising:
- a memory; and
at least one processor coupled to the memory and operative for;
obtaining incident data for at least one traffic-related incident in a selected geographic area, wherein said incident data comprises incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one traffic-related incident, wherein said obtaining incident data is carried out by the computer-aided dispatch system module executing on the computing device;
obtaining traffic data in real-time for the selected geographic area from a system of one or more traffic measurement detectors;
spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, wherein said spatially and temporally associating is carried out by the spatial-temporal module executing on the computing device; and
predicting incident duration of at least one additional traffic-related incident using one or more regression models, wherein said predicting is based on the incident duration data for the at least one traffic-related incident and incident type, one or more incident characteristics, and spatio-temporal information corresponding to the at least one additional traffic-related incident via implementing a hybrid predictive model that combines an algorithm for recursive partitioning based on at least one permutation test with a quantile regression model by employing a regression tree wherein a regression model is fitted to each final node of the tree to provide predicted values of incident duration, and wherein said predicting is carried out by the regression model module executing on the computing device. - View Dependent Claims (20)
- a memory; and
Specification