Automatically identifying associations between vehicle operating data and non-vehicle operating data

• US 10,269,240 B2
• Filed: 02/08/2017
• Issued: 04/23/2019
• Est. Priority Date: 01/30/2015
• 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): Nguyen, Nga X
• Application Number:
  US15/427,287
• Publication Number:
  US 20170148312A1
• Time in Patent Office: 804 Days
• Field of Search: 701408
• CPC Class Codes: G01C 21/34 Route searching; Route guidance
• CPC Class Codes: G01C 21/3685 the POI's being parking facilities
• CPC Class Codes: G05D 1/00 Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots drive control systems specially adapted for autonomous road vehicles B60W60/00
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: G06Q 10/047 Optimisation of routes or paths, e.g. travelling salesman problem
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0125 Traffic data processing
• CPC Class Codes: G08G 1/0137 for specific applications

Abstract

Automatically identifying associations between vehicle operating data and non-vehicle operating data may include identifying vehicle transportation network data representing a vehicle transportation network, identifying vehicle operating data reported for a plurality of vehicles, wherein the vehicle operating data includes vehicle operation records, identifying non-vehicle operating data reported for a plurality of users, wherein the non-vehicle operating data includes non-vehicle operation records, automatically identifying an association between the vehicle operating data and the non-vehicle operating data, and generating updated vehicle transportation network data based on the vehicle transportation network data.

Claims

1. A system for identifying vehicle transportation network data, 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 first vehicle transportation network data representing a vehicle transportation network;

identify vehicle operating data reported for a plurality of vehicles, wherein the vehicle operating data includes vehicle operation records, wherein each vehicle operation record from the vehicle operation records includes;

a vehicle identifier associating a vehicle with the vehicle operation record;

a passenger identifier associating a passenger with the vehicle operation record; and

a vehicle operation identifier associating a vehicle operation with the vehicle operation record, such that the vehicle performed the vehicle operation;

identify non-vehicle operating data reported for a plurality of users, wherein the non-vehicle operating data includes non-vehicle operation records, wherein each non-vehicle operation record from the non-vehicle operation records includes;

a user identifier associating a user with the non-vehicle operation record;

a destination identifier associating a destination with the non-vehicle operation record; and

a non-vehicle operation identifier associating a non-vehicle operation with the non-vehicle operation record, such that the user performed the non-vehicle operation at the destination;

automatically identify an association between the vehicle operating data and the non-vehicle operating data;

identify second vehicle transportation network data based on the first vehicle transportation network data and the association between the vehicle operating data and the non-vehicle operating data; and

output the second vehicle transportation network data for use by a vehicle to traverse a portion of the vehicle transportation network corresponding to the association, such that operating the vehicle to traverse the portion in accordance with the second vehicle transportation network data differs from operating the vehicle to traverse the portion of the vehicle transportation network in accordance with the first vehicle transportation network data.

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

generating temporal operating groups by temporally grouping the vehicle operating data and the non-vehicle operating data, such that each temporal operating group from the temporal operating groups includes;

a respective plurality of temporally grouped vehicle operations, wherein each temporally grouped vehicle operation from the plurality of temporally grouped vehicle operations includes temporal information within a period identified for the temporal operating group; and

a respective plurality of temporally grouped non-vehicle operations, wherein each temporally grouped non-vehicle operation from the plurality of temporally grouped non-vehicle operations includes temporal information within the period identified for the temporal operating group.

3. The system of claim 2, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify the association between the vehicle operating data and the non-vehicle operating data by:

for each temporal operating group from the temporal operating groups, generating respective spatial clusters;

for each spatial cluster from the respective spatial clusters;

identifying passenger identifiers, wherein each passenger identifier from the passenger identifiers is associated with a respective vehicle operation;

identifying user identifiers, wherein each user identifier from the user identifiers is associated with a respective non-vehicle operation;

identifying distinct tuples, wherein each distinct tuple from the distinct tuples includes a passenger identifier from the passenger identifiers and a user identifier from the user identifiers; and

identifying candidate tuples from the distinct tuples.

4. The system of claim 3, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to identify the candidate tuples by:

for each distinct tuple from the distinct tuples;

identifying a temporal location for the non-vehicle operation corresponding to the user identifier from the distinct tuple;

identifying a period for the vehicle operation corresponding to the passenger identifier from the distinct tuple; and

on a condition that the temporal location is within the period, including the distinct tuple in the candidate tuples.

5. The system of claim 4, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to automatically identify the association between the vehicle operating data and the non-vehicle operating data by identifying exclusive tuples, wherein identifying the exclusive tuples includes:

including each candidate tuple from the candidate tuples from each spatial cluster from the spatial clusters from each temporal operating group from the temporal operating groups in the exclusive tuples.

6. The system of claim 5, wherein identifying the exclusive tuples includes:

for each candidate tuple from the exclusive tuples;

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the passenger identifier from the candidate tuple and includes a user identifier that differs from the user identifier for the candidate tuple; and

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the user identifier from the candidate tuple and includes a passenger identifier that differs from the passenger identifier for the candidate tuple.

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

generating exclusive tuple groups, such that the passenger identifier for each exclusive tuple for a respective exclusive tuple group from the exclusive tuple groups matches each other passenger identifier for the respective exclusive tuple group, and such that the user identifier for each exclusive tuple for the respective exclusive tuple group matches each other user identifier for the respective exclusive tuple group;

identifying a cardinality of each exclusive tuple group from the exclusive tuple groups; and

associating the passenger identifier from a respective exclusive tuple group with the user identifier from the exclusive tuple group on a condition that the cardinality of the exclusive tuple group exceeds an association threshold.

8. The system of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to identify the second vehicle transportation network data by:

generating parking area association data describing an association between a parking area and a destination based on the association between the vehicle operating data and the non-vehicle operating data; and

include the parking area association data in the second vehicle transportation network data.

9. A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

identifying first vehicle transportation network data representing a vehicle transportation network;

identifying vehicle operating data reported for a plurality of vehicles, wherein the vehicle operating data includes vehicle operation records, wherein each vehicle operation record from the vehicle operation records includes;

a vehicle identifier associating a vehicle with the vehicle operation record;

a passenger identifier associating a passenger with the vehicle operation record; and

a vehicle operation identifier associating a vehicle operation with the vehicle operation record, such that the vehicle performed the vehicle operation;

identifying non-vehicle operating data reported for a plurality of users, wherein the non-vehicle operating data includes non-vehicle operation records, wherein each non-vehicle operation record from the non-vehicle operation records includes;

a user identifier associating a user with the non-vehicle operation record;

a destination identifier associating a destination with the non-vehicle operation record; and

a non-vehicle operation identifier associating a non-vehicle operation with the non-vehicle operation record, such that the user performed the non-vehicle operation at the destination;

automatically identifying an association between the vehicle operating data and the non-vehicle operating data;

identifying second vehicle transportation network data based on the first vehicle transportation network data and the association between the vehicle operating data and the non-vehicle operating data; and

outputting the second vehicle transportation network data for use by a vehicle to traverse a portion of the vehicle transportation network corresponding to the association, such that operating the vehicle to traverse the portion in accordance with the second vehicle transportation network data differs from operating the vehicle to traverse the portion of the vehicle transportation network in accordance with the first vehicle transportation network data.

10. The non-transitory computer-readable storage medium of claim 9, wherein automatically identifying the association between the vehicle operating data and the non-vehicle operating data includes:

generating temporal operating groups by temporally grouping the vehicle operating data and the non-vehicle operating data, such that each temporal operating group from the temporal operating groups includes;

a respective plurality of temporally grouped vehicle operations, wherein each temporally grouped vehicle operation from the plurality of temporally grouped vehicle operations includes temporal information within a period identified for the temporal operating group; and

a respective plurality of temporally grouped non-vehicle operations, wherein each temporally grouped non-vehicle operation from the plurality of temporally grouped non-vehicle operations includes temporal information within the period identified for the temporal operating group.

11. The non-transitory computer-readable storage medium of claim 10, wherein automatically identifying the association between the vehicle operating data and the non-vehicle operating data includes:

for each temporal operating group from the temporal operating groups, generating respective spatial clusters;

for each spatial cluster from the respective spatial clusters;

identifying passenger identifiers, wherein each passenger identifier from the passenger identifiers is associated with a respective vehicle operation;

identifying user identifiers, wherein each user identifier from the user identifiers is associated with a respective non-vehicle operation;

identifying distinct tuples, wherein each distinct tuple from the distinct tuples includes a passenger identifier from the passenger identifiers and a user identifier from the user identifiers; and

identifying candidate tuples from the distinct tuples.

12. The non-transitory computer-readable storage medium of claim 11, wherein identifying the candidate tuples includes:

for each distinct tuple from the distinct tuples;

identifying a temporal location for the non-vehicle operation corresponding to the user identifier from the distinct tuple;

identifying a period for the vehicle operation corresponding to the passenger identifier from the distinct tuple; and

on a condition that the temporal location is within the period, including the distinct tuple in the candidate tuples.

13. The non-transitory computer-readable storage medium of claim 12, wherein automatically identifying the association between the vehicle operating data and the non-vehicle operating data includes identifying exclusive tuples, wherein identifying the exclusive tuples includes:

including each candidate tuple from the candidate tuples from each spatial cluster from the spatial clusters from each temporal operating group from the temporal operating groups in the exclusive tuples.

14. The non-transitory computer-readable storage medium of claim 13, wherein identifying the exclusive tuples includes:

for each candidate tuple from the exclusive tuples;

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the passenger identifier from the candidate tuple and includes a user identifier that differs from the user identifier for the candidate tuple; and

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the user identifier from the candidate tuple and includes a passenger identifier that differs from the passenger identifier for the candidate tuple.

15. The non-transitory computer-readable storage medium of claim 14, wherein automatically identifying the association between the vehicle operating data and the non-vehicle operating data includes:

generating exclusive tuple groups, such that the passenger identifier for each exclusive tuple for a respective exclusive tuple group from the exclusive tuple groups matches each other passenger identifier for the respective exclusive tuple group, and such that the user identifier for each exclusive tuple for the respective exclusive tuple group matches each other user identifier for the respective exclusive tuple group;

identifying a cardinality of each exclusive tuple group from the exclusive tuple groups; and

associating the passenger identifier from a respective exclusive tuple group with the user identifier from the exclusive tuple group on a condition that the cardinality of the exclusive tuple group exceeds an association threshold.

16. The non-transitory computer-readable storage medium of claim 9, wherein identifying the second vehicle transportation network data includes:

generating parking area association data describing an association between a parking area and a destination based on the association between the vehicle operating data and the non-vehicle operating data; and

including the parking area association data in the second vehicle transportation network data.

17. A method comprising:

identifying first vehicle transportation network data representing a vehicle transportation network;

identifying vehicle operating data reported for a plurality of vehicles;

identifying non-vehicle operating data reported for a plurality of users;

automatically identifying an association between the vehicle operating data and the non-vehicle operating data, wherein automatically identifying the association between the vehicle operating data and the non-vehicle operating data includes;

generating temporal operating groups by temporally grouping the vehicle operating data and the non-vehicle operating data;

for each temporal operating group from the temporal operating groups, generating respective spatial clusters;

for each spatial cluster from the respective spatial clusters;

identifying distinct tuples, wherein each distinct tuple from the distinct tuples includes a passenger identifier and a user identifier; and

identifying candidate tuples from the distinct tuples;

identifying exclusive tuples from the candidate tuples; and

generating exclusive tuple groups;

identifying second vehicle transportation network data based on the vehicle transportation network data and the association between the vehicle operating data and the non-vehicle operating data; and

outputting the second vehicle transportation network data for use by a vehicle to traverse a portion of the vehicle transportation network corresponding to the association, such that operating the vehicle to traverse the portion in accordance with the second vehicle transportation network data differs from operating the vehicle to traverse the portion of the vehicle transportation network in accordance with the first vehicle transportation network data.

18. The method of claim 17, wherein:

the vehicle operating data includes vehicle operation records, wherein each vehicle operation record from the vehicle operation records includes;

a vehicle identifier associating a vehicle with the vehicle operation record;

a passenger identifier associating a passenger with the vehicle operation record; and

a vehicle operation identifier associating a vehicle operation with the vehicle operation record, such that the vehicle performed the vehicle operation; and

the non-vehicle operating data includes non-vehicle operation records, wherein each non-vehicle operation record from the non-vehicle operation records includes;

a user identifier associating a user with the non-vehicle operation record;

a destination identifier associating a destination with the non-vehicle operation record; and

a non-vehicle operation identifier associating a non-vehicle operation with the non-vehicle operation record, such that the user performed the non-vehicle operation at the destination.

19. The method of claim 18, wherein:

generating the temporal operating groups includes generating the temporal operating groups such that each temporal operating group from the temporal operating groups includes;

a respective plurality of temporally grouped vehicle operations, wherein each temporally grouped vehicle operation from the plurality of temporally grouped vehicle operations includes temporal information within a period identified for the temporal operating group; and

a respective plurality of temporally grouped non-vehicle operations, wherein each temporally grouped non-vehicle operation from the plurality of temporally grouped non-vehicle operations includes temporal information within the period identified for the temporal operating group;

identifying the distinct tuples includes;

identifying passenger identifiers, wherein each passenger identifier from the passenger identifiers is associated with a respective vehicle operation; and

identifying user identifiers, wherein each user identifier from the user identifiers is associated with a respective non-vehicle operation, and wherein each distinct tuple from the distinct tuples includes a passenger identifier from the passenger identifiers and a user identifier from the user identifiers;

identifying the candidate tuples includes;

for each distinct tuple from the distinct tuples;

identifying a temporal location for the non-vehicle operation corresponding to the user identifier from the distinct tuple;

identifying a period for the vehicle operation corresponding to the passenger identifier from the distinct tuple; and

on a condition that the temporal location is within the period, including the distinct tuple in the candidate tuples;

identifying the exclusive tuples includes;

including each candidate tuple from the candidate tuples from each spatial cluster from the spatial clusters from each temporal operating group from the temporal operating groups in the exclusive tuples; and

for each candidate tuple from the exclusive tuples;

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the passenger identifier from the candidate tuple and includes a user identifier that differs from the user identifier for the candidate tuple; and

omitting the candidate tuple from the exclusive tuples on a condition that another candidate tuple from the exclusive tuples includes the user identifier from the candidate tuple and includes a passenger identifier that differs from the passenger identifier for the candidate tuple;

generating the exclusive tuple groups includes generating the exclusive tuple groups such that the passenger identifier for each exclusive tuple for a respective exclusive tuple group from the exclusive tuple groups matches each other passenger identifier for the respective exclusive tuple group, and such that the user identifier for each exclusive tuple for the respective exclusive tuple group matches each other user identifier for the respective exclusive tuple group;

identifying a cardinality of each exclusive tuple group from the exclusive tuple groups; and

associating the passenger identifier from a respective exclusive tuple group with the user identifier from the exclusive tuple group on a condition that the cardinality of the exclusive tuple group exceeds an association threshold.

20. The method of claim 17, wherein identifying the second vehicle transportation network data includes:

generating parking area association data describing an association between a parking area and a destination based on the association between the vehicle operating data and the non-vehicle operating data; and

including the parking area association data in the second vehicle transportation network data.