KR101791947B1 - Driving evaluation method and apparatus based on fractal dimension analysis - Google Patents

Abstract

Disclosed is a method for evaluating the driving of a vehicle running by calculating a distortion degree of the driving of the vehicle with a GPS as a quantitative value by using a fractal dimension analysis and a map API in a driving evaluation apparatus based on a fractal dimension analysis. The driving evaluating method based on a fractal dimension analysis includes the steps of: collecting the dispatch data of evaluation target driving and the GPS data of the vehicle; generating a fractal dimension (VFractal) for determining the distortion degree of the evaluation target driving; generating a corrected fractal dimension (VFractal_C) by correcting the fractal dimension (VFractal); and performing driving evaluation by comparing the corrected fractal dimension (VFractal_C) with a preset reference. Accordingly, the present invention can provide a quantified vehicle driving quality index.

Description

TECHNICAL FIELD [0001] The present invention relates to a driving evaluation method and apparatus based on fractal dimension analysis,

An embodiment according to the concept of the present invention relates to an abnormal driving detection method based on fractal dimension analysis and a driving evaluation method and apparatus using the same, and more particularly, to a driving distortion estimation method of a vehicle equipped with GPS using fractal dimension analysis and map API The present invention relates to a method for estimating a running state of a vehicle by detecting an abnormal driving and a driving evaluation apparatus using the same.

In recent years, GPS devices have become common in vehicles such as taxis and watercraft trucks, so that it is possible to collect GPS data and control the route in real time. We analyzed the driver 's behavior through the collected GPS data or carried out researches on the abnormal driving route ("driving fraud detection", "abnormal driving detection", "anomalous trajectory detection" etc.

However, most of the researches use the pattern recognition and probabilistic process based on the past route data of the same source and destination to detect the abnormal path. Such a method can not be applied to various travel routes where the departure point and the destination are different, and there is a problem that a preliminary work for accumulating and calculating a large amount of data is required.

Therefore, there is a need for a technique for quantifying the path tortuosity to a single route so that the starting point and the destination can be applied to various travel routes, and a technology for detecting the abnormal route of the vehicle using the numerical value.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a driving evaluation method and apparatus capable of evaluating the quality of a single driving without having accumulated data in the past through the fractal dimension and the map API.

The driving evaluation method based on the fractal dimension analysis according to an embodiment of the present invention includes collecting data of the vehicle to be evaluated and the dispatch data of the vehicle to be evaluated; Generating a fractal dimension (VFractal) satisfying the following expression to determine a degree of distortion of the evaluation target running; Generating a corrected fractal dimension (VFractal_C) by performing a correction of the fractal dimension (VFractal) to reflect that the evaluation target travel has run on the curved road; And performing a driving evaluation by comparing the corrected and corrected fractal dimension (VFractal_C) with a predetermined reference.

The driving evaluation apparatus based on the fractal dimension analysis according to the embodiment of the present invention includes a data collecting unit for collecting the data of the running subject of the evaluation and the data of the GPS of the vehicle, A VFractal operator for generating a satisfactory fractal dimension (VFractal), a VFractal correction unit for performing correction of the fractal dimension (VFractal) and generating a corrected fractal dimension (VFractal_C), and a VFractal correction unit And a running evaluation unit for performing the running evaluation by comparison.

The method and apparatus for evaluating driving based on the fractal dimension analysis according to the present invention differs from the conventional technique for detecting the abnormal path based on accumulated travel path data of the past that is the same as the starting point and the destination, The Fractal dimension and Map API are used to quantify and provide quantified vehicle operating quality indices.

The abnormal driving detection method based on the fractal dimension analysis according to the present invention and the driving evaluation method and apparatus using the same can improve the quality of the taxi service by detecting the abnormal operation of the taxi driver in the taxi company, The abnormal situation of operation can be grasped and reflected in the work evaluation of the article, and the efficiency of the logistics can be improved by feeding back to the delivery plan.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to more fully understand the drawings recited in the detailed description of the present invention, a detailed description of each drawing is provided.
1 is a schematic diagram of a transportation management system including a travel evaluation apparatus according to an embodiment of the present invention.
2 is a functional block diagram of the running evaluation module of the running evaluation apparatus shown in FIG.
3 is a flowchart illustrating a driving evaluation method according to an embodiment of the present invention.
4 is a flowchart illustrating a driving evaluation method according to another embodiment of the present invention.
5 shows an example of a data model including vehicle movement data and running evaluation data.
Figure 6 shows the fractal curve, the Koch curve.
Fig. 7 is a diagram showing two steps of V shape.
8 shows a recommended path distance and a straight line distance between a start point and a destination point.
Fig. 9 shows an example of the vehicle movement data, and Fig. 10 shows an example of the running evaluation data calculated using the data in Fig.
Fig. 11 shows an example of a normal running evaluation result, and Fig. 12 shows an example of an abnormal running evaluation result.
13 shows a VFractal index and a driving result according to an embodiment of the present invention.

It is to be understood that the specific structural or functional description of embodiments of the present invention disclosed herein is for illustrative purposes only and is not intended to limit the scope of the inventive concept But may be embodied in many different forms and is not limited to the embodiments set forth herein.

The embodiments according to the concept of the present invention can make various changes and can take various forms, so that the embodiments are illustrated in the drawings and described in detail herein. It should be understood, however, that it is not intended to limit the embodiments according to the concepts of the present invention to the particular forms disclosed, but includes all modifications, equivalents, or alternatives falling within the spirit and scope of the invention.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms may be named for the purpose of distinguishing one element from another, for example, without departing from the scope of the right according to the concept of the present invention, the first element may be referred to as a second element, The component may also be referred to as a first component.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises" or "having" and the like are used to specify that there are features, numbers, steps, operations, elements, parts or combinations thereof described herein, But do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.

Prior to describing the present invention, the background art of the present invention will be described as follows.

The present invention relates to a driving evaluation method that provides a numerical value for evaluating a driving result of a vehicle by calculating a degree of a curvature of a traveling path as a fractal dimension.

 Fractal is a geometric structure in which the concept of self-similarity has the same shape as part and whole. It is a self-similarity and a recursiveness. It is a structure in which a small structure repeats endlessly in a form similar to the whole structure. Mandelbrot said, "How long is the coast of Britain? Statistical self-similarity and fractional dimension ", and extended the concept of Euclidean geometric dimension by presenting fractal dimension for self-similar geometry. Let N be the number of divided coatings (number of self-resembling graphics) and r be the reduction ratio of the length of one side of the segmented graphic form when resolving a graphic object into a small graphic object resembling the original graphic object. (1). &Quot; (1) "

The fractal dimension d can be expressed by the following Equation (2) by modifying [Equation 1].

For example, the fractal dimension d of a line segment represented by a straight line is obtained as follows. (1 / r)) = logN / logN = 1 by the equation (2), and the fractal dimension d is expressed by the following equation (2). The fractal dimension d of a square expressed as a plane is as follows. If you divide each side of a square with a side of one side k by k, you will have k2 squares that are self-resembling. D = logN / log (1 / r) = log (k2) / logk = 2 when the fractal dimension d is calculated by the above formula (2).

Figure 6 is a Koch curve, a fractal curve designed by Swedish mathematician Koch in 1904. Here's how to draw the Koch curve. A straight line is drawn as shown in Fig. 6 (a). 6 (a) is divided into three equal parts, and the 1/3 part of the center is deleted, and then the two sides having a length of 1/3 are connected to the outside as the two sides of the equilateral triangle, Is drawn. If the above process is repeated for four line segments having the same length, sixteen straight lines are connected and a curve as shown in (c) of FIG. 6 is drawn. Also, if the same process is repeated for 16 straight lines having the same length, 64 straight lines are connected and the curve shown in (d) of FIG. 6 is drawn. Repeatedly repeating the above procedure for each side made, the Koch curve is drawn as shown in Fig. 6 (e). Although the Koch curve is not an endless curve, the length of the Koch curve increases infinitely so that the length can not be measured. The fractal dimension (d) of the Koch curve is 1.2618 (d = (logN / log (1 / r)) by the equation (2) because the number of resembling fragments (N) )) = log4 / log3). The fractal curve, like the Koch curve, has a dimension value between 1 and 2, because it has the intermediate nature of a straight line and a plane. Fractal curves with dimension values close to 1 are close to a straight line, and as the dimension value approaches 2, the curves fill the plane with increasingly severe bending. Also, as the dimension value gets closer to 3, the fractal surface takes up a lot of space while exhibiting severe bending. In other words, the fractal dimension quantifies the degree of wobbling of the geometric structures with self-similarity, the rate at which they are hollow, and is represented by a decimal number rather than an integer. This fractal dimension represents the complexity of the system. It is a new geometry that can describe and analyze the structural irregularities in nature, and it provides a new way to describe chaos quantitatively.

 Utilizing these fractal dimensions, Vilis O. Nams proposed VFractal as an index for analyzing animal migration pathways. VFractal expresses a continuous movement path with rotation angle as a fractal dimension. Fig. 7 is a schematic representation of two steps in the shape of V in the movement path. S is a step size, Net is a straight line distance between two steps, and? Is a rotation angle between two steps. The entire travel path appears as a continuous shape of these V's. Equation (3) below is an expression that expresses two steps of the shape of V as a fractal dimension.

), s 대신 s의 평균(

)을 대입하면 전체 이동 경로에 대한 프랙탈 차원(VFractal)을 계산 수 있다.Net instead of Net (

), the average of s (

) Can be used to calculate the fractal dimension (VFractal) for the entire path.

에 GPS_n과 GPS_{n +1} 간의 평균 거리,

에 GPS_n과 GPS_{n +2} 간의 평균 거리를 대입하여 프랙탈 차원 지수(VFractal)를 계산하고, 차량 주행 결과를 정량화하였다. 이때, GPS_n과 GPS_{n +1} 간의 거리는 n번째 GPS와 n+1번째 GPS 간의 직선 거리이며, GPS_n과 GPS_{n +2} 간의 거리 n번째 GPS와 n+2번째 GPS 간의 직선 거리이다(도7 참고).In the present invention,

The average distance between GPS _n and GPS _{n +1} ,

(VFractal) was calculated by substituting the average distance between GPS _n and GPS _{n +2} and the results of vehicle driving were quantified. In this case, the GPS distance _n and _n GPS linear distance between n-th and (n + 1) th GPS GPS between _+1, GPS and GPS _{n n} n is the distance between the GPS and the second straight line distance between the n + 2 th GPS ₊₂ (FIG. 7 Reference).

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached hereto.

FIG. 1 is a schematic view of a transportation management system including a travel evaluation apparatus according to an embodiment of the present invention, and FIG. 2 is a functional block diagram of a travel evaluation module of the travel evaluation apparatus of FIG.

1, the transportation management system 10 includes a traveling evaluation apparatus 100 and a transportation management apparatus 200 according to the present invention.

The driving evaluation apparatus 100 includes a driving evaluation module 110, a database 130, and a control module (not shown). The driving evaluation apparatus 100 senses abnormal driving of the vehicle through fractal dimension analysis, .

2, the driving evaluation module 110 includes a data collection unit 111, a data generation unit 112, a VFractal calculation unit 113, a linearity calculation unit 114, a VFractal correction unit 115, (116), and a feedback performing unit (117).

Used herein may mean functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the 'to part' may refer to a logical unit of a predetermined code and a hardware resource for executing the predetermined code, and does not necessarily mean a physically connected code or a kind of hardware.

The data collecting unit 111 of the driving evaluation module 110 collects the data of the vehicle dispatching information and the position information and the data generating unit 112 of the traveling evaluating apparatus 100, under the control of the control module 190, And maps the relationship between the dispatch information and the position information to generate vehicle movement data and running evaluation data.

The VFractal operation unit 113 of the driving evaluation module 110 calculates the fractal dimension index (VFractal) of the vehicle traveling path to quantitatively determine the tortuosity of the traveling when the driving evaluation data is generated. Specifically, the average of the linear distance between the two GPS steps (the linear distance between the nth GPS and the n + 2th GPS) and the straight line distance between the GPS steps (the linear distance between the nth GPS and the n + 1th GPS) And calculates the fractal dimension index (VFractal) of the vehicle traveling path as shown in the following equation (4).

The straightness calculator 114 of the travel evaluation module 110 calculates the straightness index (SI) between the start point and the destination, which can determine the original rolled state of the road on the road when generating the running evaluation data as quantitative data, . That is, the straightness (SI) is calculated using the straight line distance D between the start point and the destination and the recommended travel distance L between the start point and the destination as shown in Equation (5) below. As the recommended driving distance L is larger than the linear distance D, the linearity SI approaches zero, indicating that the curvature of the original road is significant.

The VFractal correction unit 115 of the driving evaluation module 110 generates a corrected fractal dimension index (VFractal_C) by performing correction to numerically reflect that the driving has been performed on the originally-traveled road at the time of generating the driving evaluation data .

The running evaluation unit 116 of the driving evaluation module 110 compares the fractal dimension index (VFractal) value or the corrected fractal dimension index (VFractal_C) with the reference value of the driving evaluation to evaluate the corresponding driving.

The feedback performing unit 117 of the driving evaluation module 110 feeds back the driving evaluation results generated by the driving evaluation unit 116 to the vehicle and the dispatch module together with the driving evaluation data.

The database 130 of the travel evaluation apparatus 100 stores vehicle movement data and running evaluation data. 5 shows an example of a data model including vehicle movement data and running evaluation data. The vehicle movement data is generated from the vehicle number, the article ID, the latitude, the longitude, the GPS generation time data, the sequence generated by the travel evaluation apparatus 100, the travel ID, GPS _n and GPS _{n +1} received from the transportation management apparatus 200 Distance, distance data between GPS _n and GPS _{n + 2} , and the like. The travel evaluation data includes the travel ID, the car number, the article ID, the starting point latitude, the starting point latitude, the destination latitude, the destination longitude, the departure time and the arrival time data received from the transportation management apparatus 200, The average distance between GPS _n and GPS _{n + 1} , the average distance between GPS _n and GPS _{n +2} , the actual travel distance, the expected travel distance, the straight distance, the straightness, the fractal dimension, and the corrected fractal dimension data.

The running evaluation apparatus 100 may further include a program storage unit (not shown). Programs for controlling the operation of the travel evaluation apparatus 100 may be stored in the program storage unit. A control module (not shown) of the running evaluation apparatus 100 controls the overall operation of the running evaluation apparatus 100. [

The transportation management apparatus 200 includes a GPS reception module 210, a dispatch module 220, and a database 230 that receive GPS data of the vehicle. The database 230 of the transportation management apparatus 200 includes vehicle position data, dispatch data, and the like, and the data can be provided to the travel evaluation apparatus.

Hereinafter, a driving evaluation method based on fractal dimension analysis according to an embodiment of the present invention will be described in detail with reference to FIG.

3 is a flow chart for explaining a running evaluation method using the running evaluation apparatus shown in FIG.

(S310 to S331), a step (S333) of calculating a fractal dimension index (VFractal), a step of calculating a distortion (S380), and a step S390 of feeding back the result to the vehicle and the dispatch module.

First, the travel evaluation apparatus 100 extracts necessary data from the dispatch data generated by the transportation management system 10 and the collected GPS data of the vehicle (S310). Specifically, the travel ID, the car number, the article ID, the departure zone, the destination zone, the departure location latitude, the departure location longitude, the destination latitude, the destination longitude, the departure time and the arrival time data are extracted from the dispatch data of the transportation management apparatus 200, Generates the evaluation data, and extracts the vehicle number, the article ID, the latitude, the longitude, and the GPS generation time from the vehicle GPS data of the transportation management apparatus 200 to generate the vehicle movement data.

Next, the travel evaluation data and the vehicle movement data are mapped to the travel ID (S320). Specifically, the start time and the arrival time of the travel evaluation data are compared with the GPS creation time of the vehicle movement data, and the travel evaluation data generated by extracting from the allocation data and the vehicle movement data generated by extracting from the GPS data are stored as the travel ID TRIP_ID ).

에 GPS_n과 GPS_{n +1} 간의 평균 거리,

에 GPS_n과 GPS_{n +2} 간의 평균 거리를 대입하여 프랙탈 차원 지수(VFractal)를 계산한다.Next, the calculation of the fractal dimension index (VFractal) is performed (S330). First, in order to calculate the fractal dimension index, an average distance between GPS _n and GPS _{n +1} (hereinafter also referred to as a 'first interval') and an average distance between GPS _n and GPS _{n +2} (hereinafter also referred to as a 'second interval' Calculate the average distance. In this case, _n it refers to the GPS and GPS _n a step between the distance from the distance between the GPS _{n + 1,} and means the distance between the two steps from the _n GPS and GPS GPS distance _n between _{n +2.} Next, in Equation 3,

The average distance between GPS _n and GPS _{n +1} ,

And calculate the fractal dimension index (VFractal) by substituting the average distance between GPS _n and GPS _{n +2} .

The running is evaluated using the fractal dimension index (VFractal) value (S380). That is, it is possible to evaluate whether it is normal driving or abnormal driving. At this time, in order to correct the distortion of the fractal dimension index (VFractal) value due to the GPS information error, a value smaller than 1 can be set to 1, and a value larger than 2 can be set to 2. As the fractal dimension index (VFractal) value is closer to 1, it can be evaluated that the running quality is good because it runs near to a straight line. When the fractal dimension index (VFractal) value is close to 2, Can be evaluated as bad.

Next, the driving evaluation result is fed back (S390). Real-time feedback to the vehicle and dispatch module along with actual values can be a reference for subsequent dispatch and driving. System administrators can periodically analyze these figures to find ways to improve driving quality.

Hereinafter, a driving evaluation method based on fractal dimension analysis according to another embodiment of the present invention will be described in detail with reference to FIG. In the case of using the running evaluation method according to the embodiment of FIG. 3, the VFractal value is calculated to be close to 2 even in the case of running on a road with severe bending or in a normal running, and the running quality is undervalued. This problem can be solved by the running evaluation method according to the embodiment of FIG. 4, in particular, calculating the straightness index (S440) and correcting the fractal dimension index (VFractal_C) (S450). Description of the contents overlapping with those described above will be omitted.

First, the travel evaluation apparatus 100 collects (S410) the required data from the dispatch data and the GPS data of the vehicle generated and collected by the transportation management system 10, and maps it to the travel ID (S420).

Next, in order to determine the degree of tortuosity of the evaluation target, calculation of the fractal dimension index (VFractal) is performed by calculating the average of the distances between the two GPS steps and the distance between the GPS steps (S430).

Next, an arithmetic operation of the linearity SI between the source and destination, which represents the original rolled state of the travel road of the evaluation target travel, is performed (S450). Specifically, the straight line distance D between the start point and the destination is calculated (S451), the recommended travel distance L between the start point and the destination is calculated using the map API (S453) And calculates the linearity (SI = D / L) by dividing by the distance L (S455). As the traveling road is closer to the straight line, the straightness becomes closer to '1', and as the curvature of the traveling road becomes larger, the straightness becomes closer to '0'. The recommended mileage can be calculated using the map API as the mileage of the recommended route between the origin and destination. At this time, the recommended route may be a recommended route at the time of driving evaluation or a recommended route at the time of driving. And may be a recommended route reflecting the traffic situation or the road condition at the time of the corresponding driving.

The mileage is extracted using a map API such as the Google Direction API. If the GIS program is embedded in the transportation management system 10, the mileage can be extracted using the API provided by the program.

Next, the fractal dimension index (VFractal, d) is corrected using the following Equation (6) to reflect the fact that the evaluation target traveled in the original rounded road, and a corrected fractal dimension index (VFractal_C) is generated (S460).

FIG. 9 shows the vehicle movement data for the running ID " 352164 " of the Vancouver taxi generated through the above process, and FIG. 10 is the running evaluation data generated through the above process. The vehicle movement data in Fig. 9 includes the mapped traveling ID, the distance s between GPS _n and GPS _{n + 1} , and the straight distance Net between GPS _n and GPS _{n +2} by comparing the GPS generation time. The running evaluation data in FIG. 10 shows the average distance between s and Net calculated in FIG. 9, the fractal dimension index (VFractal) calculated using the s, the straight line calculated using the straight distance and the recommended travel distance, the VFractal index and the straight line And a corrected fractal dimension index (VFractal_C) calculated by using the corrected fractal dimension index. In FIG. 10, since VFractal_C is 1.7494, it can be considered that the traveling has relatively high tortuosity.

Next, the corrected fractal dimension index (VFractal_C) is compared with the reference value of the driving evaluation to evaluate the corresponding driving (S480). The standard value of the driving evaluation can be set by the system administrator from 1 to 2. For example, if the system administrator sets the reference value to 1.7, the travel ID " 352164 " will be determined as abnormal travel, and if the reference value is set to 1.8, the travel will be determined as normal travel. Fig. 11 shows an example of the normal running evaluation result, and Fig. 12 shows an example of the abnormal running evaluation result.

It is also possible to set a plurality of reference values for the running evaluation and carry out the running evaluation using a plurality of ratings. For example, by setting two reference values, it is possible to carry out the driving evaluation with 'poor / normal / good', and by setting four reference values, the driving evaluation is performed as' very bad / bad / normal / good / .

Next, the driving evaluation result thus determined is fed back to the vehicle and the dispatch module together with the driving evaluation data (S490). By feedback in real time, it is possible to refer to the next dispatching and driving, and the system manager can periodically analyze the driving evaluation data to find ways to improve driving quality.

13 shows an example of the VFractal index and the driving result. 13 (a) and 13 (b), in which VFractal and VFractal_C are close to 1, the traveling path is close to a straight line, and the distances between the actual traveling distance and the recommended traveling distance are almost the same, and the difference between VFractal and VFractal_C is very small. Figures 13 (c) and 13 (d) show cases where the driving quality is not high but are in the normal driving category. The VFractal_C value is lowered by reflecting the somewhat bumpy road condition that crosses the bridge when leaving the island. Figs. 13 (e) and 13 (f) clearly show that the vehicle can be judged as abnormal driving. It can be judged that the vehicle is running abnormally even with the naked eye, and the corrected VFractal_C value is close to 2, indicating that the travel path is highly distorted. FIGS. 13 (g) and 13 (h) show an example in which the travel characteristic in which the geographical characteristic of the Vancouver was corrected by the correction operation and the VFractal value was judged to be 2 or more before the correction was evaluated as the normal running after the correction was performed.

As described above, in the driving evaluation method and apparatus according to the present invention, the quality of a single driving can be evaluated even if there is no accumulated data in the past through the fractal dimension and the map API.

The fractal dimension analysis based driving evaluation method described above can be implemented as a program that can be executed in a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium.

The multiprocessing program is stored in the recording medium, and the recording medium may be a storage medium such as a magnetic storage medium (e.g., ROM, floppy disk, hard disk, etc.), an optical reading medium (e.g. CD-ROM, Media. In addition, the recording medium may be distributed and distributed to a network-connected computer system so that a computer-readable instruction set can be stored and executed in a distributed manner.

The block diagrams disclosed herein may be construed to those skilled in the art to conceptually represent circuitry for implementing the principles of the present invention. Likewise, any flow chart, flow diagram, state transitions, pseudo code, etc., may be substantially represented in a computer-readable medium to provide a variety of different ways in which a computer or processor, whether explicitly shown or not, It will be appreciated by those skilled in the art.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

10: Transportation management system 100: Driving evaluation device
110: travel evaluation module 200: transportation management device

Claims (10)

In a transportation management system for collecting location information of a vehicle and planning a dispatch,
Collecting the data of the vehicle to be evaluated and the data of the GPS of the vehicle;
Generating a fractal dimension (VFractal) satisfying the following expression to determine a degree of distortion of the evaluation target running; And
And performing a driving evaluation by comparing the fractal dimension (VFractal) with a preset reference.
[Mathematical Expression]

The method according to claim 1,
Further comprising the step of correcting the fractal dimension (VFractal) to generate a corrected fractal dimension (VFractal_C) so as to reflect the driving of the road subject to the evaluation,
Wherein the step of performing the driving evaluation includes performing a driving evaluation by comparing the corrected fractal dimension (VFractal_C) with a preset reference. 3. The method of claim 2,
The step of performing the correction to generate a corrected fractal dimension (VFractal_C)
Calculating a straightness degree (SI) between a starting point and a destination point of the evaluation running traveling which indicates the degree of bending of the traveling road of the evaluation subject running; And
And generating the corrected fractal dimension (VFractal_C) satisfying the following equation using the linearity (SI).
[Mathematical Expression]

The method of claim 3,
The step of calculating the linearity (SI)
Calculating a straight line distance (D) between the starting point and the destination of the evaluation target travel;
Calculating a recommended travel distance (L) between the starting point and the destination of the evaluation target travel using the map API; And
And calculating the straightness (SI) satisfying the following formula using the straight line distance (D) and the recommended running distance (L).
[Mathematical Expression]

5. The method according to any one of claims 1 to 4,
And feeding back the result of the driving evaluation. A data collecting unit for collecting the data of the running subject of the evaluation and the data of the GPS of the vehicle,
A VFractal operation unit for generating a fractal dimension (VFractal) satisfying the following expression to determine the degree of distortion of the evaluation target running; and
And a running evaluation unit that compares the fractal dimension (VFractal) with a preset reference to perform a running evaluation.
[Mathematical Expression]

The method according to claim 6,
A straightness degree calculating section for calculating a straightness degree (SI) between a starting point and a destination of the evaluation running traveling which indicates the degree of bending of the traveling road of the evaluation target traveling,
(VFractal) that satisfies the following formula using the linearity SI to reflect the running of the road subject to the evaluation, and generates a corrected fractal dimension (VFractal_C) Further comprising a VFractal correction unit,
Wherein the driving evaluation unit compares the corrected fractal dimension (VFractal_C) with a predetermined reference to perform a driving evaluation.
[Mathematical Expression]

8. The method of claim 7,
The straightness calculation unit calculates the straight line SI satisfying the following formula using the straight line distance D between the starting point and the destination of the evaluation target running and the recommended running distance L between the starting point and the destination of the evaluation target running, Based on the fractal dimension analysis.
[Mathematical Expression]

9. The method according to any one of claims 6 to 8,
And a feedback performing unit for feedbacking the result of the driving evaluation. A computer-readable recording medium storing a program for executing the method according to any one of claims 1 to 4.

Images