Route prediction using network history

• US 8,200,425 B2
• Filed: 12/31/2008
• Issued: 06/12/2012
• Est. Priority Date: 12/31/2008
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Overgoor, Frank, Meider, Andreas, Uljee, Rob
• Primary Examiner(s): Shah, Amee A
• Application Number:
  US12/347,951
• Publication Number:
  US 20100169000A1
• Time in Patent Office: 1,259 Days
• Field of Search: 701/202, 701/204, 701/410, 701/434, 705/330
• US Class Current: 701/410
• CPC Class Codes: G01C 21/34 Route searching; Route guidance
• CPC Class Codes: G06Q 10/083 Shipping

Abstract

A computer system may include a route reader configured to determine routes of a route database, the routes being associated with a combination of route characteristics including an origin, destination, and transported object type, the routes representing actual transportations of transported objects of the transported object type from the origin to the destination within a time period. The computer system also may include a route selector configured to determine a route set from among the routes, based on additional route characteristics, and a route analyzer configured to determine a subset of routes from among the route set, based on a total transit time of each route within the route set, and configured to separate each of the subset of routes into route events of each route, each route event being associated with a route event completion time. The computer system also may include a route predictor configured to determine a predictive event completion time for each route event, based on the associated route event completion time, and further configured to use the predictive event completion time for each route event to compile a predictive route transit time and thereafter provide the predictive route transit time as a prediction for future transporting of transported objects of the transported object type between the origin and the destination.

Claims

1. A computer system comprising:

one or more processors;

one or more computer-readable storage media storing computer instructions translatable by the one or more processors;

a route reader configured to determine routes of a route database for transportation of objects by shipping transport, the routes being associated with a combination of route characteristics including an origin, destination, and transported object type, the routes representing actual transportations by shipping transport of the transported objects of the transported object type from the origin to the destination within a time period;

a route selector configured to determine a route set from among the routes, based on additional route characteristics;

a route analyzer configured to determine a subset of routes from among the route set, based on a total transit time of each route within the route set, and configured to separate each of the subset of routes into route events of each route, the route events including at least loading, transporting, and unloading the objects, and each route event being associated with a route event completion time; and

a route predictor configured to determine a predictive event completion time for each route event, based on the associated route event completion time, and further configured to use the predictive event completion time for each route event to compile a predictive route transit time and thereafter provide the predictive route transit time as a prediction for future transporting by shipping transport of the transported objects of the transported object type between the origin and the destination.

2. The computer system of claim 1 wherein the route characteristics include at least one of a service type of the transportation and a number of intermediate locations including in each route between the origin and the destination.

3. The computer system of claim 1 wherein the additional route characteristics include at least one of a total transit time of each of the routes, an average total transit time of each of the routes, a standard deviation associated with each route of the routes, a frequency of use of each of the routes within the time period, a frequency of exceptions within each of the routes, a recency of exceptions within each of the routes, and a duration of route events within each of the routes.

4. The computer system of claim 1 wherein the route selector is configured to use a combination of the additional route characteristics in which a weighting is applied to at least one of the additional route characteristics to reflect a relative importance thereof in obtaining the predictive route transit time.

5. The computer system of claim 1 wherein the route analyzer is configured to determine the subset of routes by selecting the subset as being within a multiple of a standard deviation of the average total transit time of routes of the route set.

6. The computer system of claim 1 wherein the route analyzer is configured to determine the subset of routes based on one or more of an average total transit time of each route of the set of routes, a standard deviation associated with each route of the set of routes, a frequency of exceptions within each route of the set of routes, a recency of exceptions within each route of the set of routes, and a duration of route events within each route of the set of routes.

7. The computer system of claim 1 wherein the route events include one or more of a transit time between each stop of each route and planned activities that occur at each stop of each route.

8. The computer system of claim 1 wherein the route predictor is configured to determine the predictive event completion time based on an average route event completion time of each associated route event within each route of the subset of routes.

9. The computer system of claim 1 wherein the time period comprises a plurality of time periods and wherein the predictive route transit time is periodically calculated based on a most recent one of the time periods, and is stored in a predictive route transit time database to be provided therefrom using a web service.

10. The computer system of claim 1 comprising:

a request handler configured to receive a request for the predictive route transit time as received from a graphical user interface (GUI); and

a view generator configured to provide the predictive route transit time using the GUI.

11. A computer program product for forecasting routes for transporting objects, the computer program product being tangibly embodied on a computer-readable medium and including executable code that, when executed, is configured to cause a data processing apparatus to:

determine a route set from among routes of a route database for transportation of objects by shipping transport, the routes being associated with a combination of route characteristics including an origin, destination, and transported object type, the routes representing actual transportations by shipping transport of the transported objects of the transported object type from the origin to the destination within a time period;

determine a subset of routes from among the route set, based on a total transit time of each route within the route set;

separate each of the subset of routes into route events of each route, the route events including at least loading, transporting, and unloading the objects, and each route event being associated with a route event completion time;

determine a predictive event completion time for each route event, based on the associated route event completion time;

use the predictive event completion time for each route event to compile a predictive route transit time; and

provide the predictive route transit time as a prediction for future transporting by shipping transport of the transported objects of the transported object type between the origin and the destination.

12. The computer program product of claim 11 wherein the executable code is configured to cause the data processing apparatus to use a combination of the additional route characteristics in which a weighting is applied to at least one of the additional route characteristics to reflect a relative importance thereof in obtaining the predictive route transit time.

13. The computer program product of claim 11 wherein the executable code is configured to cause the data processing apparatus to determine the set of routes based on a standard deviation of total transit times of each physical route of the routes, and based on a frequency of use of each physical route of the routes, within the time period.

14. The computer program product of claim 11 wherein the executable code is configured to cause the data processing apparatus to determine the subset of routes by selecting the subset as being within a multiple of a standard deviation of the average total transit time of routes of the route set.

15. The computer program product of claim 11 wherein the additional route characteristics include at least one of a total transit time of each of the routes, an average total transit time of each of the routes, a standard deviation associated with each route of the routes, a frequency of use of each of the routes within the time period, a frequency of exceptions within each of the routes, a recency of exceptions within each of the routes, and a duration of route events within each of the routes.

16. The computer program product of claim 11 wherein the executable code is configured to cause the data processing apparatus to determine the predictive event completion time based on an average route event completion time of each associated route event within each route of the subset of routes.

17. The computer program product of claim 11 wherein the predictive route transit time is periodically calculated based on a most recent one of the time period, and is stored in a predictive route transit time database to be provided therefrom using a web service.

18. The computer program product of claim 11 wherein the executable code is configured to cause the data processing apparatus to receive a request for the predictive route transit time as received from a graphical user interface (GUI), and provide the predictive route transit time using the GUI.

19. A method comprising:

determining, at a server, a route set from among routes of a route database for transportation of objects by shipping transport, the routes being associated with a combination of route characteristics including an origin, destination, and transported object type, the routes representing actual transportations by shipping transport of the transported objects of the transported object type from the origin to the destination within a time period;

determining a subset of routes from among the route set, based on a total transit time of each route within the route set;

separating each of the subset of routes into route events of each route, the route events including at least loading, transporting, and unloading the objects, and each route event being associated with a route event completion time;

determining a predictive event completion time for each route event, based on the associated route event completion time;

using the predictive event completion time for each route event to compile a predictive route transit time; and

providing the predictive route transit time as a prediction for future transporting by shipping transport of the transported objects of the transported object type between the origin and the destination.

20. The method of claim 19 wherein the providing the predictive route transit time comprises providing the predictive route transit time using one or both of a web service and a graphical user interface (GUI).