Estimation of transit demand models for enhancing ridership

• US 8,571,918 B2
• Filed: 07/16/2012
• Issued: 10/29/2013
• Est. Priority Date: 06/06/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Naphade, Milind, Sahu, Sambit
• Primary Examiner(s): Meinecke Diaz, Susanna M
• Application Number:
  US13/549,777
• Publication Number:
  US 20120310707A1
• Time in Patent Office: 470 Days
• Field of Search: 705/7.31
• US Class Current: 705/7.31
• CPC Class Codes: G06F 16/29 Geographical information databases

Abstract

A method of estimating a transit demand graph includes collecting conditional information that includes at least one condition that when satisfied converts at least one non-rider into a rider, generating a non-rider transit demand graph by satisfying one of the conditions, and generating a normalized transit demand graph from the non-rider transit demand graph and a rider transit demand graph. The riders use public transit and the non-riders do not use public transit. The non-rider transit demand graph shows the demand of the non-riders for a public transit route. The rider transit demand graph shows the demand of riders for the same public transit route.

Claims

1. A method of estimating a transit demand graph, the method comprising:

collecting non-rider conditional information that includes at least one non-rider condition that when satisfied converts at least one non-rider into a rider, wherein non-riders do not use a public transit route;

generating, by a processor, a non-rider transit demand graph by satisfying one of the non-rider conditions, wherein the non-rider transit demand graph shows the demand of the non-riders for the public transit route;

collecting rider conditional information that includes at least one rider condition that when satisfied converts at least one rider into a non-rider, wherein riders use the public transit route, wherein collecting the rider conditional information comprises parsing survey results for feedback on changes proposed by a survey that would encourage a rider to become a non-rider and deriving the rider conditions from the feedback;

generating, by a processor, a rider transit demand graph by satisfying one of the rider conditions, wherein the rider transit demand graph shows the demand of the riders for the public transit route; and

generating a normalized transit demand graph from the non-rider transit demand graph and a rider transit demand graph.

2. The method of claim 1, wherein collecting the non-rider conditional information comprises:

parsing survey results for feedback on changes proposed by a survey that would encourage a non-rider to become a rider; and

deriving the non-rider conditions from the feedback.

3. The method of claim 1, wherein generating the non-rider transit demand graph comprises:

determining non-riders that are within a predetermined distance of the public transit route;

determining a subset of the non-riders that become riders when the non-rider condition is satisfied; and

generating the non-rider transit demand graph from the sub-set of non-riders and the public transit route.

4. The method of claim 3, wherein determining the non-riders comprises:

comparing a current position of a mobile phone against a subsequent position of the same mobile phone to determine a speed; and

determining a non-rider when the speed is outside a range expected for a transit vehicle.

5. The method of claim 1, wherein the rider transit demand graph is generated by:

determining riders that are within a predetermined distance of the public transit route; and

generating the rider transit demand graph from the determined riders and the public transit route.

6. The method of claim 5, wherein determining the riders comprises:

comparing positions of a mobile phone against waypoints of the route; and

determining a rider when the positions of the mobile phone correspond with those of the waypoints.

7. The method of claim 6, wherein the positions correspond when a majority of the positions of the mobile phone are considered to be inside a transit vehicle.

8. The method of claim 1, wherein the rider transit demand graph is generated based on a tally of a number of fare cards used on a transit vehicle following the route.

9. A non-transitory computer-readable medium tangibly embodying a program of machine-executable instructions to perform method steps for estimating a transit demand graph, the method steps comprising:

collecting non-rider conditional information that includes at least one non-rider condition that when satisfied converts at least one non-rider into a rider, wherein non-riders do not use a public transit route;

generating a non-rider transit demand graph by satisfying one of the non-rider conditions, wherein the non-rider transit demand graph shows the demand of the non-riders for the public transit route;

collecting rider conditional information that includes at least one rider condition that when satisfied converts at least one rider into a non-rider, wherein riders use the public transit route, wherein collecting the rider conditional information comprises parsing survey results for feedback on changes proposed by a survey that would encourage a rider to become a non-rider and deriving the rider conditions from the feedback;

generating a rider transit demand graph by satisfying one of the rider conditions, wherein the rider transit demand graph shows the demand of the riders for the public transit route; and

generating a normalized transit demand graph from the non-rider transit demand graph and a rider transit demand graph.

10. The non-transitory computer-readable medium of claim 9, wherein collecting the non-rider conditional information comprises:

parsing survey results for feedback on changes proposed by a survey that would encourage a non-rider to become a rider; and

deriving the non-rider conditions from the feedback.

11. The non-transitory computer-readable medium of claim 9, wherein generating the non-rider transit demand graph comprises:

determining non-riders that are within a predetermined distance of the public transit route;

determining a subset of the non-riders that become riders when the non-rider condition is satisfied; and

generating the non-rider transit demand graph from the sub-set of non-riders and the public transit route.

12. The non-transitory computer-readable medium of claim 11, wherein determining the non-riders comprises:

comparing a current position of a mobile phone against a subsequent position of the same mobile phone to determine a speed; and

determining a non-rider when the speed is outside a range expected for a transit vehicle.

13. The non-transitory computer-readable medium of claim 9, wherein the rider transit demand graph is generated by:

determining riders that are within a predetermined distance of the public transit route; and

generating the rider transit demand graph from the determined riders and the public transit route.

14. The non-transitory computer-readable medium of claim 13, wherein determining the riders comprises:

comparing positions of a mobile phone against waypoints of the route; and

determining a rider when the positions of the mobile phone correspond with those of the waypoints.

15. The non-transitory computer-readable medium of claim 14, wherein the positions correspond when a majority of the positions of the mobile phone are considered to be inside a transit vehicle.

16. The non-transitory computer-readable medium of claim 9, wherein the rider transit demand graph is generated based on a tally of a number of fare cards used on a transit vehicle following the route.