Using telematics data to identify a type of a trip

Patent metadata

Field	Value
Publication number	US-9900747-B1
Application number	US-201715596384-A
Country	US
Kind code	B1
Filing date	May 16, 2017
Priority date	May 16, 2017
Publication date	Feb 20, 2018
Grant date	Feb 20, 2018

Abstract

Among other things, an operation of a computational device in identifying a type of a given trip of a person is improved. Historical information is stored about prior trips of the person or of other people or both. The historical information is based on other than recorded motion data of the trips. Features are derived about the prior trips from the historical information. Features indicative of the type of the given trip are identified by the computational device. The type of the given trip is identified based on the features derived from the historical information.

First claim

The invention claimed is:

1. A method for improving operation of a computational device in classifying a vehicle mode of a given trip of a person, the vehicle mode comprising a car mode or non-car mode, the method comprising
storing in a storage device, historical information about prior car mode trips and non-car mode trips of the person or of other people or both,
by computer, deriving features about the prior trips from the historical information, the features being indicative of the car mode or non-car mode of the given trip being identified by the computational device,
storing in persistent storage a classification model representing the features,
receiving from a velocity sensor information about the given trip, the information comprising data representing periods of constant minimum speed,
receiving from a path sensor information representing straightness of a trajectory during the given trip based on noisiness in a direction orthogonal to a direction of instantaneous movement along the trajectory,
receiving from accelerometers and GPS devices, information representative of a distribution of jerk,
receiving from a location measuring device, information representing dispersion and density of location measurements,
deriving features about the given trip from the received information, and
causing the computational device to execute the classification model to classify the vehicle mode of the given trip either as a car mode or as a non-car mode based on the features derived about the given trip, without requiring the person to have identified the vehicle mode of prior trips of the person.

2. The method of claim 1 in which the stored historical information is indicative of historical patterns of the prior trips.

3. The method of claim 2 in which the historical patterns are associated with one or more of: times of the prior trips, locations of the prior trips, or trajectories of the prior trips.

4. The method of claim 1 in which the features comprise one or more of: the person having been a passenger in one or more of the prior trips, a locality of one or more of the prior trips, a contextual proximity of one or more of the prior trips, trip similarities of one or more of the prior trips, calendrical variations of the prior trips, or phone usage patterns.

5. The method of claim 1 in which the features comprise the dates, days-of-week, or times of the prior trips.

6. The method of claim 1 in which the features comprise labels of the prior trips provided by the person or other people or both.

7. The method of claim 1 in which the features comprise identifications of the types of the prior trips.

8. The method of claim 1 comprising classifying a role of the person in the trip.

9. The method of claim 8 in which the role of the person comprises a role as a driver or a role as a passenger.

10. The method of claim 1 in which one of the features comprises idle vibration indicative of a characteristic of a vehicle.

11. The method of claim 1 in which one of the features comprises tilting.

12. The method of claim 1 in which one of the features comprises usage of a mobile device during the given trip.

13. The method of claim 1 in which one of the features comprises straightness of a trajectory during the given trip.

Assignees

• Cambridge Mobile Telematics Inc
• Cambridge Mobile Telematics Inc

Inventors

• Park Jun Geun

Classifications

• G01C21/3423

  Multimodal routing · CPC title

• G07C5/085

  using electronic data carriers · CPC title

• G08G1/015

  with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles · CPC title

• G08G1/0129

  for creating historical data or processing based on historical data · CPC title

• G01C21/3484

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title