Anomaly detection for road user charging systems

• US 9,261,375 B2
• Filed: 04/01/2010
• Issued: 02/16/2016
• Est. Priority Date: 04/01/2010
• Status: Expired due to Fees

• Current Assignee: Maplebear Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Appel, Todd M., Ashby, Duncan A., Chun, So Yeon, Naphade, Milind R., Nash, Richard J., Sheopuri, Anshul, Thornqvist, Anders, Vuyk, Martin
• Primary Examiner(s): SHEIKH, ASFAND M
• Application Number:
  US12/752,524
• Publication Number:
  US 20110246058A1
• Time in Patent Office: 2,147 Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3453 Special cost functions, i.e. other than distance or default speed limit of road segments
• CPC Class Codes: G07B 15/06 Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems
• CPC Class Codes: G07B 15/063 using wireless information transmission between the vehicle and a fixed station identification of vehicles G08G
• CPC Class Codes: G08G 1/096827 where the route is computed onboard

Abstract

A computer readable medium embodies a program of machine-readable instructions executable by a processing apparatus to perform operations including determining information corresponding to a number of differences in distances between ending points of journeys taken by a vehicle and starting points of consecutive journeys taken by the vehicle, and transmitting one or more representations of the information. Another computer readable medium tangibly includes instructions for, for each of a number of vehicles, receiving one or more scores corresponding to a vehicle, and determining a ranked list containing at least a portion of the scores, and outputting the ranked list. Another computer readable medium includes instructions for, for each of a number of vehicles, receiving information corresponding to a vehicle, using one or more metrics, calculating one or more values from the received information, and communicating one or more representations of the one or more value to one or more entities.

Claims

1. A non-transitory computer-readable storage medium tangibly embodying a program of machine-readable instructions executable by a digital processing on-board unit having a device for measuring a position of a vehicle and a transceiver to cause the digital processing on-board unit to perform operations comprising:

determining information characterizing a plurality of differences in measured positions of the vehicle between ending points of journeys taken by the vehicle and starting points of consecutive, new journeys taken by the vehicle, said ending points and said starting points being determined by the measuring device aboard the vehicle, said ending points being the last known positions of the vehicle in the journeys and said starting points being the positions of the vehicle when the measuring device is enabled at the start of consecutive, new journeys, said differences in measured positions arising where said ending points of journeys and said starting points of consecutive, new journeys as measured by the measuring device aboard the vehicle do not coincide with one another, said plurality of differences in measured positions being quantified by a plurality of respective distance differences;

transmitting at least one representation of the information characterizing the plurality of distance differences;

receiving from a server at a central location at least one global representation of information characterizing a plurality of distance differences for a plurality of vehicles;

calculating at least one metric for detecting fraud in the use of the device for measuring the position of the vehicle using the at least one global representation when the vehicle makes a new journey by identifying any anomaly among the plurality of the distance difference for the vehicle; and

transmitting a flag message to the server at the central location when potential fraud is detected to trigger enforcement at the central location through the automatic generation of a fine and an associated letter to a possible abuser of said device for measuring the position of the vehicle.

2. The non-transitory computer-readable storage medium of claim 1, wherein:

determining information further comprises determining a mean and a standard deviation corresponding to the plurality of respective distance differences; and

transmitting further comprises transmitting at least one representation of the mean and the standard deviation.

3. The non-transitory computer-readable storage medium of claim 1, wherein calculating said at least one metric determines at least one score;

and wherein transmitting the flag message further comprises transmitting at least one representation of the at least one score.

4. The non-transitory computer-readable storage medium of claim 3, further comprising determining whether the at least one score is greater than at least one threshold, and wherein transmitting the flag message further comprises transmitting, for only those at least one scores greater than the at least one threshold, at least one representation of the at least one score.

5. The non-transitory computer-readable storage medium of claim 3, wherein the at least one global representation of information comprises a global mean and a global standard deviation.

6. The non-transitory computer-readable storage medium of claim 5, where one of the at least one metrics comprises the following:

Φ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(max x_j), where Φ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(●

) is an inverse normal cumulative distribution function using the received global mean, μ

, and the received global standard deviation, σ

, max is a maximum function, and each x_j is a distance difference for a journey j.

7. The non-transitory computer-readable storage medium of claim 6, where one of the at least one metrics comprises the following:

Π

_k=1^KΦ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(P_k (X)), where Π

_k=1^K (●

) is a product function, K is a total number of distance differences for the plurality of journeys, and X is a distance difference distribution for the plurality of journeys.

8. The non-transitory computer-readable storage medium of claim 5, where one of the at least one metrics comprises the following:

Π

_k=1^KΦ

<sub>(μ

,σ

)</sub>(P_k (X)), where Π

_k=1^K(●

) is a product function, where K is a total number of distance differences for the plurality of journeys, where Φ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(●

) is an inverse normal cumulative distribution function using the received global mean, μ

,and the received global standard deviation, σ

, and X is a distance difference distribution for the plurality of journeys.

9. An on-board unit comprising:

a device for measuring a position of a vehicle;

a transceiver;

at least one memory comprising instructions; and

at least one processor operatively coupled to the at least one memory, the at least one processor configured by the instructions to cause the on-board unit to perform operations comprising;

determining information characterizing a plurality of differences in measured positions of the vehicle between ending points of journeys taken by the vehicle and starting points of consecutive, new journeys taken by the vehicle, said ending points and said starting points being determined by the measuring device aboard the vehicle, said ending points being the last known positions of the vehicle in the journeys and said starting points being the positions of the vehicle when the measuring device is enabled at the start of consecutive, new journeys, said differences in measured positions arising where said ending points of journeys and said starting points of consecutive, new journeys as measured by the measuring device aboard the vehicle do not coincide with one another, said plurality of differences in measured positions being quantified by a plurality of respective distance differences;

transmitting at least one representation of the information characterizing the plurality of distance differences;

receiving from a server at a central location at least one global representation of information characterizing a plurality of distance differences for a plurality of vehicles;

calculating at least one metric for detecting fraud in the use of the device for measuring the position of the vehicle using the at least one global representation when the vehicle makes a new journey by identifying any anomaly among the plurality of the distance difference for the vehicle; and

transmitting a flag message to the server at the central location when potential fraud is detected to trigger enforcement at the central location through the automatic generation of a fine and an associated letter to a possible abuser of said device for measuring the position of the vehicle.

10. The on-board unit of claim 9, wherein:

determining information further comprises determining a mean and a standard deviation corresponding to the plurality of differences; and

transmitting further comprises transmitting at least one representation of the mean and the standard deviation.

11. The on-board unit of claim 9, wherein calculating said at least one metric determines at least one score;

and wherein transmitting the flag message further comprises transmitting at least one representation of the at least one score.

12. The on-board unit of claim 11, wherein said processor is further configured to determine whether the at least one score is greater than at least one threshold, and wherein transmitting the flag message further comprises transmitting, for only those at least one scores greater than the at least one threshold, at least one representation of the at least one score.

13. The on-board unit of claim 9, wherein the at least one global representation of information comprises a global mean and a global standard deviation.

14. The on-board unit of claim 13, where one of the at least one metrics comprises the following:

Φ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(max x_j), where Φ

<sub>(μ

,σ

)</sub><sup>−

1</sup>(●

) is an inverse normal cumulative distribution function using the received global mean, μ

, and the received global standard deviation, σ

, max is a maximum function, and each x_j is a distance difference for a journey j.

15. The on-board unit of claim 14, where one of the at least one metrics comprises the following:

Π

_k=1^KΦ

<sub>(μ

,σ

)</sub>(P_k (X)) , where Π

_k=1^K (●

) is a product function, K is a total number of distance differences for the plurality of journeys, and X is a distance difference distribution for the plurality of journeys.

16. The on-board unit of claim 13, where one of the at least one metrics comprises the following:

Π

_k=1^KΦ

<sub>(μ

,σ

)</sub>(P_k (X)), where Π

_k=1^K (●

) is a product function, where K is a total number of distance differences for the plurality of journeys, where Φ

<sub>(μ

,σ

)</sub>(●

) is an inverse normal cumulative distribution function using the received global mean, μ

, and the received global standard deviation, σ

, and X is a distance difference distribution for the plurality of journeys.