Pattern detection using probe data

• US 9,778,658 B2
• Filed: 03/13/2015
• Issued: 10/03/2017
• Est. Priority Date: 03/13/2015
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan North America Incorporated (Nissan Motor Co., Ltd.)
• Inventors: Thakur, Siddharth, Saito, Daisuke
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Kong, Sze-Hon
• Application Number:
  US14/657,127
• Publication Number:
  US 20160265922A1
• Time in Patent Office: 935 Days
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G05D 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287

Abstract

A method and apparatus for associating a person with a portion of transportation network information based on vehicle operating information are described. The information includes a plurality of destinations. First vehicle operating information for a vehicle is identified, which information includes a first plurality of vehicle operations occurring during a first plurality of time windows. First values for a plurality of features are extracted from the first plurality of vehicle operations. A portion of the vehicle transportation network is associated with an owner/operator of the vehicle based on the first values. For consecutive time windows thereafter, second values for the features are extracted from second vehicle operating information for the vehicle that includes a second plurality of vehicle operations occurring during the consecutive time windows. Based on changes, a determination can be made as to whether an identity of the person associated with the vehicle has changed over time.

Claims

1. A vehicle comprising:

a processor configured to execute instructions stored on a non-transitory computer readable medium to;

identify vehicle transportation network information representing a vehicle transportation network, wherein the vehicle transportation network includes a plurality of destinations, and wherein identifying the vehicle transportation network information includes identifying the vehicle transportation network information such that the vehicle transportation network information describes an association of a portion of the vehicle transportation network with a person associated with the vehicle based at least in part on an automatically identified association between the person associated with the vehicle and vehicle operating information of the vehicle;

determine whether the person associated with the vehicle changes over time by;

obtaining the vehicle operating information for the vehicle over defined time periods;

extracting a plurality of features of the vehicle operating information for each of the time periods; and

calculating a probability that the person associated with the vehicle has changed during each of the time periods by comparing respective features of the plurality of features for a time period with respective features for a previous time period;

determine a target destination from the plurality of destinations based on the vehicle transportation network information and the person associated with the vehicle; and

identify a route from an origin to the target destination in the vehicle transportation network using the vehicle transportation network information; and

a trajectory controller configured to operate the vehicle to travel from the origin to the target destination using the route, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify an association between the person and the vehicle operating information by;

obtaining an energy use of the vehicle during a first plurality of time windows;

summing the energy use occurring during each time window of the first plurality of time windows;

arranging the energy use sequentially in an order of the first plurality of time windows to form a pattern; and

associating the person with the pattern formed by the energy use during the first plurality of time windows.

2. The vehicle of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to determine whether the person associated with the vehicle changes over time by:

obtaining an energy use of the vehicle during a second plurality of time windows;

comparing the energy use during the second plurality of time windows with the pattern; and

determining that the person associated with the vehicle changed after an end of the first plurality of time windows based on changes in the energy use during the second plurality of time windows as compared to the pattern.

3. The vehicle of claim 2, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to update the association of the portion of the vehicle transportation network with the person responsive to determining that the person associated with the vehicle changed.

4. The vehicle of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify an association between the person and the vehicle operating information by:

obtaining a plurality of origin-destination pairs for the vehicle during a first plurality of time windows, each of the plurality of origin-destination pairs comprising a location within the vehicle transportation network from which the vehicle departs for a trip paired with a location within the vehicle transportation network at which the vehicle arrives at an end of the trip; and

associating the person with a pattern formed by the plurality of origin-destination pairs over the first plurality of time windows.

5. The vehicle of claim 4, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to form the pattern by:

ranking the plurality of origin-destination pairs by frequency of occurrence; and

omitting an origin-destination pair of the plurality of origin-destination pairs from the pattern when a frequency of occurrence of the origin-destination pair is below a minimum value.

6. The vehicle of claim 4, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify an association between the person and the vehicle operating information by:

obtaining a plurality of origin-destination pairs of the vehicle during a second plurality of time windows;

comparing the origin-destination pairs obtained during the second plurality of time windows with the pattern; and

determining that the person associated with the vehicle changed after an end of the first plurality of time windows based on changes in locations of the origin-destination pairs during the second plurality of time windows as compared to the pattern; and

wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to update the association of the portion of the vehicle transportation network with the person responsive to determining that the person associated with the vehicle changed.

7. The vehicle of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify an association between the person and the vehicle operating information by:

obtaining at least one location at which the vehicle is stationary for more than a minimum time period during a first plurality of time windows; and

associating the person with a pattern formed by the at least one location during the first plurality of time windows.

8. The vehicle of claim 7, wherein the first plurality of time windows comprises each of a plurality of consecutive months and wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to form the pattern by filtering the at least one location by at least one of a time of day, and day of the week, and a minimum number of hours for which the vehicle is stationary at the at least one location.

9. The vehicle of claim 8, wherein the time of day is arrival at a destination during morning hours, the day of the week includes weekdays, and the minimum number of hours is at least three hours.

10. The vehicle of claim 8, wherein the time of day is nighttime and the minimum number of hours is at least three hours.

11. The vehicle of claim 1, wherein the vehicle is an autonomous vehicle.

12. The vehicle of claim 1, wherein the plurality of features comprise location-based features that identify a time and a duration at a location, and the processor is configured to execute instructions stored on the non-transitory computer readable medium to determine whether the person associated with the vehicle changes over time by:

calculating the probability by determining whether a location obtained in the time period represents a change in location from the previous time period.

13. A vehicle comprising:

a processor configured to execute instructions stored on a non-transitory computer readable medium to;

identify vehicle transportation network information representing a vehicle transportation network, wherein the vehicle transportation network includes a plurality of destinations, and wherein identifying the vehicle transportation network information includes identifying the vehicle transportation network information such that the vehicle transportation network information describes an association of a portion of the vehicle transportation network with a person associated with the vehicle based at least in part on an automatically identified association between the person associated with the vehicle and vehicle operating information of the vehicle, wherein the portion of the vehicle transportation network includes at least some of the plurality of destinations;

determine a change in the person associated with the vehicle, based at least in part by;

obtaining an energy use of the vehicle during a first plurality of time windows;

summing the energy use occurring during each time window of the first plurality of time windows;

arranging the energy use occurring during each time window of the first plurality of time windows in a first sequence of energy use over time;

obtaining the energy use of the vehicle during a second plurality of time windows subsequent to the first plurality of time windows;

summing the energy use occurring during each time window of the second plurality of time windows;

arranging the energy use occurring during each time window of the second plurality of time windows in a second sequence of energy use over time; and

determining that the second sequence of energy use over time is different from the first sequence of energy use over time;

determine a target destination from the plurality of destinations based on the vehicle transportation network information, the target destination based on the change in the person associated with the vehicle; and

identify a route from an origin to the target destination in the vehicle transportation network using the vehicle transportation network information; and

a trajectory controller configured to operate the vehicle to travel from the origin to the target destination using the route.

14. The vehicle of claim 13, wherein the processor configured to execute instructions stored on a non-transitory computer readable medium to determine the change in the person associated with the vehicle by:

identifying first vehicle operating information for the vehicle, wherein the first vehicle operating information includes a first plurality of vehicle operations occurring during a first plurality of time windows;

extracting first values for a plurality of features from the first plurality of vehicle operations;

associating a portion of the vehicle transportation network with the person associated with a single vehicle based on the first values;

for consecutive time windows after the first plurality of time windows, extract second values for the plurality of features from second vehicle operating information for the vehicle, wherein the second vehicle operating information includes a second plurality of vehicle operations occurring during the consecutive time windows; and

determining that an identity of the person associated with the vehicle has changed over time based on changes between the second values for the plurality of features and the first values for the plurality of features.

15. A system for generating vehicle transportation network information, the system including:

a memory including a non-transitory computer readable medium; and

a processor configured to execute instructions stored on the non-transitory computer readable medium to;

identify vehicle transportation network information representing a vehicle transportation network, the vehicle transportation network information including a plurality of destinations;

identify first vehicle operating information for a single vehicle, wherein the first vehicle operating information includes a first plurality of vehicle operations occurring during a first plurality of time windows;

extract first values for a plurality of features from the first plurality of vehicle operations;

associate a portion of the vehicle transportation network with a person associated with the single vehicle based on the first values;

for consecutive time windows after the first plurality of time windows, extract second values for the plurality of features from second vehicle operating information for the single vehicle, wherein the second vehicle operating information includes a second plurality of vehicle operations occurring during the consecutive time windows;

determine whether an identity of the person associated with the single vehicle has changed over time based on changes between the second values for the plurality of features and the first values for the plurality of features; and

responsive to determining that the identity of the person has changed, remove an association of the portion of the vehicle transportation network within the vehicle transportation network information with the person associated with the single vehicle.

16. The system of claim 15, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to determine whether the identity of the person associated with the single vehicle has changed over time based on changes between the second values for the plurality of features and the first values for the plurality of features by:

generating a probability value based on the changes between the second values and the first values.

17. The system of claim 15, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:

identify the first vehicle operating information for the single vehicle by identifying a plurality of origin-destination pairs occurring during the first plurality of time windows;

extract the first values for a plurality of features from the first plurality of vehicle operations by extracting a location of the origin and a location of the destination for the plurality of origin-destination pairs by filtering out those origin-destination pairs occurring below a minimum number of times in the first vehicle operating information; and

extract the second values for the plurality of features by extracting a location of the origin and a location of the destination for a plurality of origin-destination pairs from the second vehicle operating information for the single vehicle.

18. The system of claim 15, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:

identify the first vehicle operating information for the single vehicle by identifying a plurality of origin-destination pairs occurring during the first plurality of time windows;

extract the first values for a plurality of features from the first plurality of vehicle operations by extracting a time at which a first destination of the plurality of origin-destination pairs is reached and a length of time for which the single vehicle remains stationary at the first destination; and

extract the second values for the plurality of features by extracting a time at which a second destination of a plurality of origin-destination pairs from the second vehicle operating information for the single vehicle is reached and a length of time for which the single vehicle remains stationary at the second destination.