METHOD OF PROCESSING AND ANALYSING VEHICLE DRIVING BIG DATA AND SYSTEM THEREOF

• US 20150317844A1
• Filed: 02/06/2015
• Published: 11/05/2015
• Est. Priority Date: 05/02/2014
• Status: Active Grant

• Current Assignee: Kookmin University
• Original Assignee: Kookmin University
• Inventors: CHOI, EUN MI, CHO, WON HEE
• Granted Patent: US 9,600,541 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C

Abstract

Provided is a method of processing and analyzing vehicle driving big data, the method including: refining vehicle driving data of raw data; acquiring statistical data based on the refined vehicle driving data; and performing mining analysis based on at least one of the refined vehicle driving data and the acquired statistical data.

Claims

1. A method of processing and analyzing vehicle driving big data, comprising:

refining vehicle driving data of raw data;

acquiring statistical data based on the refined vehicle driving data; and

performing mining analysis based on at least one of the refined vehicle driving data and the acquired statistical data.

2. The method of claim 1, wherein the vehicle driving data include identification data and sensing data;

the identification data include at least one of records for fields of a vehicle identification number, a vehicle type, a vehicle registration number, a transportation business operator registration number, and a driver identification code, shipping document information, name of shipper and commodity; and

the sensing data include at least one of records for fields of a travel distance, a driving time, starting time, a data acquisition period, a data acquisition time, a speed, an RPM, a break signal, a position, an azimuth, and acceleration, location of the vehicle, OBD-II(On Board Diagnostics II) information.

3. The method of claim 2, wherein the refining includes:

detecting an outlier by determining whether the record for each field of the sensing data has a value within a limit range; and

removing the record or correcting the record to correspond to the value in the limit range when the record detected as the outlier has a value beyond the limit range.

4. The method of claim 3, wherein the refining includes:

detecting the outlier by deviation-comparing the sequent records for each field of the refined sensing data, after the correcting; and

removing the record detected as the outlier through the deviation comparison.

5. The method of claim 3, wherein the refining includes:

detecting the outlier by comparing records of fields having a correlation in the refined sensing data, after the correcting; and

removing the record detected as the outlier through the correlation comparison.

6. The method of claim 1, wherein the acquired statistical data include driving statistical data and tendency statistical data;

the driving statistical data include at least one of records for fields of a daily travel distance, a total driving time, an average speed, a maximum speed, and a maximum RPM, mileage, fuel consumption, energy consumption, Exhaust emissions, driving area, distance between cars; and

the tendency statistical data include at least one of records for fields of the number of overspeed, the number of dangerous overspeed, the number of long-term overspeed, the number of rapid acceleration, the number of rapid deceleration, the number of quick start, the number of rapid stopping, the number of overtaking, the number of course changing, the number of rapid rotation, the number of idling, the number of high RPM, a distance between cars.

7. The method of claim 6, wherein the acquiring of the statistical data includes:

generating the statistical data by statistically calculating the refined vehicle driving data;

determining whether the records for each field are repetitively calculated within a predetermined time in the generated statistical data; and

correcting the records determined to be repetitively calculated to one calculated value.

8. The method of claim 6, wherein the performing of the mining analysis includes:

classifying driving tendencies of the vehicle driver for each type based on the tendency statistical data; and

indexing the tendency degree of the vehicle driver with respect to each of the classified types.

9. The method of claim 8, wherein the performing of the mining analysis includes:

generating index information indicating a result indexed for the classified types, after the indexing; and

analyzing a correlation of at least one of the fields of the tendency statistical data and the index information.

10. The method of claim 6, wherein the performing of the mining analysis includes:

analyzing a repeated pattern based on a specific period, based on the refined vehicle driving data and the fields of the acquired statistical data; and

analyzing a driving tendency of the vehicle driver at the specific period based on the repeated pattern.

11. The method of claim 6, wherein the acquired statistical data further include history data including records for accident history and maintenance history fields;

and

the performing of the mining analysis includes;

generating a learning mode for predicting a change in at least one of the accident history and maintenance history fields, based on the refined vehicle driving data and the acquired statistical data; and

analyzing at least one of the accident risk and a maintenance time of the vehicle by using the learning model.

12. The method of claim 11, wherein the performing of the mining analysis includes generating index information indicated by indexing the degree of the accident risk or whether the maintenance time is coming based on the analysis result, after analyzing at least one of the accident risk and the maintenance time.

13. The method of claim 6, wherein the performing of the mining analysis includes:

extracting location information of the vehicle based on the refined vehicle driving data and the acquired statistical data; and

analyzing a space increasing accident risk and increasing air pollution based on the extracted location information of the vehicle and the fields of the tendency statistical data.

14. The method of claim 6, wherein the performing of the mining analysis includes:

extracting location information of the vehicle based on the refined vehicle driving data and the acquired statistical data; and

analyzing the driving tendencies of the drivers for each administrative district, based on the extracted location information of the vehicle, the tendency statistical data, and map data.

15. The method of claim 8, wherein the performing of the mining analysis includes:

generating index information indicated by indexing the tendency degree of the classified type; and

analyzing a distribution state of the generated index information, based on the transportation business operator registration number field of the refined vehicle driving data.

16. The method of claim 8, wherein the performing of the mining analysis includes:

generating index information indicated by indexing the tendency degree of the classified type; and

classifying before and after the driver of the vehicle recognizes the generated index information to detect a change of the generated index information, the refined vehicle driving data, and the acquired statistical data and analyzing a change of the driving tendency of the vehicle driver based on the detection result.

17. The method of claim 1, further comprising:

before the refining of the vehicle driving data, collecting vehicle driving data acquired from a vehicle driving recorder or a sensor.

18. The method of claim 1, wherein the acquired statistical data include statistical data related to at least one of fuel consumption and Exhaust emissions, and the acquired statistical data is classified according to at least one of driver, transportation business operator, region, road, respectively;

and

the performing of the mining analysis includes generating at least one of Eco driving information of driver and predicted overloading information of vehicle based on the statistical data related to at least one of fuel consumption and Exhaust emissions.

19. The method of claim 1, wherein the acquired statistical data include statistical data related to diagnostic code of OBD-II(On Board Diagnostics II), and the acquired statistical data is classified according to at least one of driver, transportation business operator, model of vehicle, model year of vehicle, respectively;

and

the performing of the mining analysis includes generating at least one of predicted information regarding abnormality of vehicle, accident risk, and vehicle maintenance based on the statistical data related to diagnostic code.

20. A system of processing and analyzing vehicle driving big data, comprising:

as the system of processing and analyzing big data by using vehicle driving data,

a big data storing unit configured to store the vehicle driving data of raw data; and

a big data processing unit configured to refine the vehicle driving data of the raw data stored in the big data storing unit, acquire statistical data based on the refined vehicle driving data, and perform mining analysis based on at least one of the refined vehicle driving data and the acquired statistical data.