ONBOARD VEHICLE DATA MINING, SOCIAL NETWORKING, AND PATTERN-BASED ADVERTISEMENT

• US 20110258044A1
• Filed: 06/30/2011
• Published: 10/20/2011
• Est. Priority Date: 04/28/2004
• Status: Active Grant

• Current Assignee: Agnik LLC
• Original Assignee: Agnik LLC
• Inventors: KARGUPTA, HILLOL
• Granted Patent: US 8,478,514 B2
• Time in Patent Office: Days
• US Class Current: 705/14.49
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C

Abstract

The present invention is an improvement of methods and systems using mobile and distributed data stream mining algorithms for mining continuously generated data from different components of a vehicle. The system is designed for both on-board and remote mining and management of the data in order to (1) detect the effect of various engine parameters on fuel consumption behavior, (2) predictive classification of driving patterns and associative indexing of driver performance matrix, (3) resource-constrained anomaly detection for onboard health monitoring, (4) vehicle-to-vehicle social networking and distributed data mining, (5) adaptive placement of advertisements based on vehicle performance profile and (6) onboard emissions analytics computation for wireless emissions monitoring and smog test.

Claims

1. A multi-agent distributed data mining system for monitoring the performance of vehicles and drivers and fleets. The apparatus has the following components:

a. Onboard Module for Data Stream Mining;

This component monitors vehicle diagnostic data coming out of OBD/J1708/J1939 ports, GPS data, and accelerometer (also known as G-sensor data) and performs the following data stream mining tasks to generate onboard results (analytics);

i. Onboard Data Stream Mining for detecting the effects of various engine parameters on fuel consumption.

ii. Onboard Predictive Classification of Driving Patterns and Associative Indexing of Driver Performance Matrix.

iii. Resource-constrained Anomaly Detection for Onboard Predictive Vehicle Health Monitoring.

iv. Onboard Vehicle Emission Data Analysis.

v. Automated Adaptive Algorithm Generation and Management.

b. Web-based Presentation of the Results of Onboard Data Analysis and User-Interaction. This component allows presentation of the analytics to the user using a web-based interface.

c. Onboard and remote-server-based techniques for advertising products and services that are triggered by the patterns identified by the vehicle data analysis.

d. Pattern-driven Web-based and Onboard vehicle-to-vehicle social networking and collective computation.

2. The system of claim 1, further comprising a module for vehicle health scoring and generating MineFleet Fault Codes onboard the vehicle based on the predictive models constructed from the vehicle operating condition and various diagnostic data, reporting those to the remote server, and presenting the information to the user using either stand-alone or web-based interface.

3. The system of claim 1, further comprising a module for construction of predictive emissions profile of a vehicle onboard the vehicle, reporting those to the remote server and web server via a wired or wireless connection for wireless emissions monitoring and smog test.

4. The system of claim 1, further comprising a module for wireless smog test and reporting through email or query processing interface to determine whether or not a vehicle meets the smog test requirements.

5. The system of claim 1, further comprising a module for fuel consumption analysis and modeling for different types of driving behavior and different vehicle operating conditions, reporting that to the server, and presenting the information to the user using either stand-alone or web-based interface.

6. The system of claim 1, further comprising a module for fuel consumption analysis and modeling the effect of driver behavior and vehicle system parameters on fuel consumption, reporting that to the server, and presenting the information to the user using either stand-alone or web-based interface.

7. The system of claim 1, further comprising a module for identifying the top reasons for getting poor fuel economy by analyzing the vehicle maintenance data and presenting those to the users.

8. The system of claim 1, further comprising a method for onboard driving pattern detection from speeding, acceleration, braking, idling, turning characteristics and various vehicle operating parameters for evaluating, scoring, and indexing the driver behavior.

9. The method of claim 8, further comprising of the zero calibration and orientation calibration methods, onboard sharp turn detection, onboard rapid acceleration and braking detection, onboard tailgating detection and onboard risky lane change detection.

10. The system of claim 1, further comprising a module for social networking among vehicles for sharing vehicle-related information among a group of vehicles for generating collective statistics about the class of vehicles.

11. The system of claim 1, further comprising a module for social networking among vehicles for vehicle-related information among a group of vehicles and their owners for buying a one or more vehicles, selling one or more vehicles, discussing one or more types of vehicles, maintaining one or more vehicles and performing other vehicle operations-related tasks.

12. The system of claim 1, further comprising a module for Onboard and remote-server-based techniques for playing single and multi-party games based on the vehicle data.

13. The system of claim 1, further comprising a module for building predictive models linking vehicle diagnostic data with vehicle maintenance data for detecting frequent and infrequent maintenance events.

14. The system of claim 1, further comprising a module for identifying the expensive maintenance operations and the possible reasons behind those at the remote server.

15. The system of claim 1, further comprising a module for generating vehicle health reports onboard the vehicle for short drive tests, used for a quick check of the current vehicle health conditions for the vehicle, reporting that to the server, and presenting the information to the user using either stand-alone or web-based interface.

16. The reports generated by the module of claim 15 to be used for the purpose of buying and selling a vehicle.

17. The system of claim 1 further comprising a module for detecting fuel tank events onboard the vehicle, reporting that to the server, and presenting the information to the user using either stand-alone or web-based interface.

18. The system of claim 1, further comprising a method for onboard and remote server-based adaptive techniques for advertising products and services that are triggered by the patterns identified by the vehicle performance data analysis.

19. The method of claim 18 for determining if an advertisement is relevant to a target vehicle performance profile, the method comprising of identifying targeting information for the advertisement;

analyzing the content of the target vehicle profile to identify a set of one or more topics for the target vehicle profile;

comparing the targeting information to the set of one or more topics to determine if a match exists; and

determining that the advertisement is relevant to the target vehicle profile if the match exists.

20. The method of claim 18, wherein the advertisement belongs to an advertiser, and wherein identifying targeting information comprises receiving a list of topics from the advertiser.