KR20230115390A - Method of providing driver's dangerous driving behavior value reflecting continuous driving time - Google Patents

Abstract

The present invention relates to a method for providing risky driving behavior values of a driver, and more particularly, to a method for providing risky driving behavior values of a driver reflecting continuous driving time. To this end, in the method for providing risky driving behavior values of a driver, the server apparatus 100 receives and stores driving data from at least one vehicle 10 (S100); Classifying the traffic of the vehicle 10 based on the driving data by the risky driving behavior quantification unit 130 (S120); Generating, by the risky driving behavior quantification unit 130, continuous driving time for each divided traffic (S140); Calculating, by the risky driving behavior quantification unit 130, an entropy weight (ω _ij ) of each of the classified dangerous driving behaviors (S160); Calculating, by the risky driving behavior quantification unit 130, a risky driving behavior value based on the risky driving behavior for each passage and the entropy weight (ω _ij ) (S180); and providing, by the server controller 110, the calculated dangerous driving behavior values to the outside (S200).

Description

Method of providing driver's dangerous driving behavior value reflecting continuous driving time

The present invention relates to a method for providing risky driving behavior values of a driver, and more particularly, to a method for providing risky driving behavior values of a driver reflecting continuous driving time.

In the past, the Korea Transportation Safety Authority made it mandatory as of January 1, 2011 to install a digital driving recorder on commercial vehicles in accordance with the Traffic Safety Act. The driving data collected from the vehicle equipped with the digital driving recorder was uploaded through a USB or mobile communication network.

The driving data collected in this way is collected and collectively processed in the driving record analysis system of the Korea Transportation Safety Authority. The Korea Transportation Safety Authority's driving record analysis system identifies and manages each driver's driving habits based on the collected information to prevent traffic accidents and provides analysis information to drivers to induce safe driving.

1 is a block diagram of a quantification structure for calculating risky driving behavior values. As shown in FIG. 1, conventionally, risky driving behavior represented by overspeed, long-term overspeed, rapid acceleration, rapid deceleration, sudden stop or sudden start has been quantified.

In such a conventional system and process, when generating safe driving scores, risky driving behaviors were selected and risky driving behavior weights were calculated. However, in the past, fixed weights made as shown in [Table 1] were used through expert questionnaires.

Risky driving behavior weight Number of dangerous driving occurrences per 100 km (example) run 1 run 2 run 3 Speeding Speeding 0.083 0 8.7 15.4 long-term speeding 0.083 0 0 0 sudden acceleration sudden acceleration 0.18 0 5.1 14.8 sudden start 0.18 0 0 0 rapid deceleration rapid deceleration 0.264 11.4 31.1 68.5 Sudden stop 0.264 0 0 0 doubling sudden left turn 0.228 0 2.2 2.8 sharp right turn 0.228 0 3.2 5.3 refueling turn 0.228 1.8 0 3.2 change to express train outrun 0.245 0 0 1.2 sudden course change 0.245 1.8 7.7 14.6 Number of dangerous driving occurrences per operation 15.0 58.0 125.8 safe driving index 96.1 87.1 71.5

That is, conventionally, the safe driving score was calculated using the weights in [Table 1] and [Equation 1].

[Equation 1]

Safe driving score = 100 - Σ (number of dangerous driving occurrences per 100 km × dangerous driving weight)

However, in the conventional method using fixed weights, not only does the driver's mid-time rest not be considered, but variable weights according to various environmental changes cannot be reflected due to the fixed weights. As a result, the reliability of the safe driving score was lowered, and there was a disadvantage that it was not well used for secondary data processing (eg, used in a big data system).

1. Republic of Korea Patent Publication No. 10-2017-0024292 (system and method for estimating safe driving index of vehicle driver by reflecting safety evaluation information provided from at least one passenger), 2. Republic of Korea Patent Publication No. 10-2021-0071222 (Vehicle driving score prediction program and its method).

Therefore, the present invention has been made to solve the above problems, and the problem to be solved by the present invention is to classify the driver's continuous driving unit as a trip, and utilize it to reflect the driver's risk of continuous driving time It is to provide a driving behavior value providing method.

Another object of the present invention is to provide a method for providing a risky driving behavior value of a driver reflecting continuous driving time for varying weights based on collected driving data.

However, the technical problems to be achieved in the present invention are not limited to the above-mentioned technical problems, and other technical problems not mentioned will be clear to those skilled in the art from the description below. You will be able to understand.

In order to achieve the above technical problem, in a method for providing risky driving behavior values of a driver, the server apparatus 100 receives and stores driving data from at least one vehicle 10 (S100); Classifying the traffic of the vehicle 10 based on the driving data by the risky driving behavior quantification unit 130 (S120); Generating, by the risky driving behavior quantification unit 130, continuous driving time for each divided traffic (S140); Calculating, by the risky driving behavior quantification unit 130, an entropy weight (ω _ij ) of each of the classified dangerous driving behaviors (S160); Calculating, by the risky driving behavior quantification unit 130, a risky driving behavior value based on the risky driving behavior for each passage and the entropy weight (ω _ij ) (S180); and providing, by the server controller 110, the calculated dangerous driving behavior values to the outside (S200).

In addition, the driving data includes at least one of driving time information, vehicle driving and behavior information, GPS location information, travel rest information, and dangerous driving behavior information.

Further, the vehicle travel and behavior information includes at least one of travel distance during travel, travel time during travel, cumulative travel distance, vehicle speed, acceleration, and engine speed.

In addition, the travel rest information includes information on the location of a rest stop and a drowsy shelter and information on whether the rest stop or a drowsy shelter has been visited.

In addition, the dangerous driving behavior information includes at least one of sudden stop, sudden course change, number of times of acceleration, average acceleration, average sudden acceleration, and sudden acceleration deviation.

In addition, in the passage classification step (S120), the case where the vehicle 10 visits a rest area or a sleepy rest area and the case where the vehicle 10 passes through a toll gate on a highway is divided into other traffic.

In addition, the step of calculating the entropy weight (ω _ij ) (S160) is the step of calculating the matrix D and distribution probability (p _ij ) of the risky driving behavior index (x _ij ) according to the following [Equation 2] ( S162);

[Equation 2]

,

,

calculating entropy (E _ij ) for each risky driving behavior index (x _ij ) according to the following [Equation 3] (S164); and

[Equation 3]

,

,

Calculating an entropy weight (ω _ij ) according to the following [Equation 4] (S166);

[Equation 4]

Including, where i represents passage from 1 to m, and j represents risky driving behavior items from 1 to n.

In addition, the step of calculating the risky driving behavior value (S180) includes calculating the risky driving behavior value (y _i ) for each passage according to the following [Equation 5] (S182); and

[Equation 5]

and calculating the average of the risky driving behavior values y _i for each passage as the risky driving behavior value Y (S184); where X _k is the risky driving behavior information value.

In addition, the step of providing the risky driving behavior value (S200) further includes providing a safety score according to the following equation, where safety score = 1 - risky driving behavior value.

In addition, the step of providing risky driving behavior values (S200) includes providing them to the vehicle; providing evaluation of a vehicle operating on a specific road or specific area; and providing evaluation for each vehicle classified into trucks, buses, and passenger cars; includes at least one of

According to an embodiment of the present invention, a driver's risky driving evaluation can be performed based on the continuous driving time, so that a more accurate risky driving behavior value can be calculated.

In addition, various data situations can be more accurately reflected by applying a variable weight. The risky driving behavior values calculated in this way can be continuously utilized in big data systems or machine learning algorithms.

In addition, it can be provided individually as a safe driving index, or can be used to objectify drivers operating on the road by group evaluation or vehicle group evaluation such as cargo/bus/passenger cars. In addition, it can be used to calculate the risky facility improvement points through relative comparison values such as risky area calculation through the risky driving behavior value by region.

However, the effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and together with the detailed description of the present invention serve to further understand the technical idea of the present invention, the present invention is the details described in such drawings should not be construed as limited to
1 is a block diagram of a quantification structure for calculating risky driving behavior values;
2 is a schematic configuration diagram of a system for providing risky driving behavior values of a driver reflecting continuous driving time according to an embodiment of the present invention;
3 is a schematic block diagram of the server device 100 in FIG. 2;
Figure 4a is a classification of traffic when the driver does not stop for more than 15 minutes at a rest area or a sleepy rest area on the highway,
4B is a classification of traffic when the driver stops for more than 15 minutes at a rest area or a sleepy rest area on the highway;
5 is a schematic flowchart of a method for providing risky driving behavior values of a driver reflecting continuous driving time according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily carry out the present invention. However, since the description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiment can be changed in various ways and can have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, the scope of the present invention should not be construed as being limited thereto.

The meaning of terms described in the present invention should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element. It should be understood that when an element is referred to as “connected” to another element, it may be directly connected to the other element, but other elements may exist in the middle. On the other hand, when an element is referred to as being “directly connected” to another element, it should be understood that no intervening elements exist. Meanwhile, other expressions describing the relationship between components, such as “between” and “immediately between” or “adjacent to” and “directly adjacent to” should be interpreted similarly.

Singular expressions should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as “comprise” or “having” refer to a described feature, number, step, operation, component, part, or It should be understood that it is intended to indicate that a combination exists, and does not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless defined otherwise. Terms defined in commonly used dictionaries should be interpreted as consistent with meanings in the context of related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present invention.

Configuration of the embodiment

Hereinafter, the configuration of a preferred embodiment will be described in detail with reference to the accompanying drawings.

2 is a schematic configuration diagram of a system for providing risky driving behavior values of a driver reflecting continuous driving time according to an embodiment of the present invention. As shown in FIG. 2 , driving data of the vehicle 10 is transmitted to the server device 100 through the network 20 . The vehicle 10 targets all vehicles capable of driving on the road, such as passenger cars, buses, trucks, and heavy equipment vehicles. Such a vehicle 10 is provided with OBU (not shown), DTG (Digital Tacho Graph, digital driving recorder), IoT (Internet of Things) sensor, driver's smartphone web, etc. to wirelessly transmit driving data generated by itself. .

The driving data includes driving time information of the vehicle 10, vehicle driving and behavior information, GPS location information, travel rest information, and risky driving behavior information. In addition, vehicle operation and behavior information includes travel distance during travel, travel time during travel, cumulative travel distance, vehicle speed, acceleration, and engine speed. Travel rest information includes location information of rest areas and drowsiness shelters and information on whether or not the rest areas or drowsiness shelters have been visited. Dangerous driving behavior information includes sudden stop, sudden course change, number of times of acceleration, average acceleration, average sudden acceleration, and sudden acceleration deviation. More specifically, [Table 2] defines examples and specifications of operation data composed of RAW data.

Main Category middle category data explanation unit Vehicle operation and movement information
(in seconds) Driving time information collection date vehicle operation date YYYYMMDD collection time vehicle operation time HHMMSS Vehicle operation and behavior information Mileage so far Distance traveled so far (since the start of the current trip to the present) km Driving time so far Driving time so far (since the start of the current trip to the present) minute cumulative driving distance Cumulative mileage (total mileage of the vehicle after using the app) km vehicle speed instantaneous speed kph acceleration acceleration m/s2 RPM Engine revolutions per minute (RPM) RPM GPS location information Movement coordinates (latitude) Vehicle location information (latitude) degree Movement coordinates (longitude) Vehicle location information (longitude) degree Movement coordinates (altitude) Vehicle location information (altitude) m GPS speed GPS speed m/s GPS bearing GPS bearing degree Traffic Pause Information Location information such as rest areas and sleepy shelters branch visit 1, otherwise 0 1/0 dangerous driving
behavior information Sudden stop The number of cases where the speed decreased to 0 by decelerating more than 7.5 km/h per second episode sudden course change When the speed is over 30km/h, the direction of travel is left/right Change the lane more than sec, and the cumulative angle for 5 seconds The number of cases where acceleration and deceleration were less than 2km/h per second and less than sec. episode number of accelerations The number of times acceleration has occurred episode average acceleration Average acceleration when accelerated operation occurs m/s2 rapid acceleration average Average acceleration when acceleration of 11km/h or more per second occurs km/h rapid acceleration deviation Acceleration deviation when acceleration of 11km/h or more per second occurs km/h

The network 20 may be a base station capable of wireless communication, the Internet, an intranet, or the like, and may be a 4G or 5G communication network.

The server device 100 is a computer device installed in the central control center. The server device 100 receives driving data from the plurality of vehicles 10 in real time, at regular intervals, or whenever an event occurs. The server device 100 calculates risky driving behavior values based on the driving data.

FIG. 3 is a schematic block diagram of the server device 100 in FIG. 2 . As shown in FIG. 3, the communication unit 120 is a wired/wireless communication module capable of communicating with the network 20 (eg: TCP/IP communication module, 4G, 5G communication module, Wi-Fi, Bluetooth module, LAN module, intranet module, etc.) am.

The risky driving behavior quantification unit 130 is a component that calculates risky driving behavior values based on the received driving data. The risky driving behavior quantification unit 130 includes a driving data storage unit 132, a traffic data storage unit 134, and a weight storage unit 136 in detail. Each component of the risky driving behavior quantification unit 130 interlocks with the server control unit 110 to read, calculate, and store data. The risky driving behavior quantification unit 130 includes a hard disk, flash memory, and the like.

The risky driving behavior provider 140 is a component that provides the calculated risky driving behavior value to the outside. The risky driving behavior provider 140 may be configured to provide the calculated risky driving behavior value to a corresponding vehicle. Optionally, it can be provided to vehicles operating on specific roads (eg, curved roads, sloped roads) or specific areas (eg, accident-prone roads), and can be provided for evaluation of these vehicles. And optionally, it can be provided for vehicle-specific evaluation, such as trucks, buses, and passenger cars.

The server control unit 110 performs calculation, judgment, and comparison operations for calculating risky driving behavior values, and controls the server device 100 . The server control unit 110 may be a CPU, AP, microcomputer, or the like.

Operation of the embodiment

Hereinafter, the operation of the preferred embodiment will be described in detail with reference to the accompanying drawings. 5 is a schematic flowchart of a method for providing risky driving behavior values of a driver reflecting continuous driving time according to an embodiment of the present invention. As shown in FIG. 5 , first, the server device 100 receives travel data from the plurality of vehicles 10 in operation and stores the travel data in the travel data storage unit 132 (S100).

Next, the risky driving behavior quantification unit 130 classifies the traffic of the vehicle 10 based on the travel data, and stores the classified travel data in the travel data storage unit 134 (S120). For example, FIG. 4A is a classification of traffic when a driver does not stop for 15 minutes or more at a rest area or a rest area on a highway. In the case of FIG. 4A , passage 1 is divided into from the start of driving to before entering the expressway toll gate, passage 2 is divided into from entering to exiting the toll gate, and passage 3 is divided into from entering the toll gate to stopping driving on a general road. That is, in the case of FIG. 4A , the corresponding vehicle 10 can be regarded as not stopping at a rest area or a sleepy rest area. At this time, the driving score is calculated as passage 1 + passage 2 + passage 3.

On the other hand, FIG. 4B is a classification of traffic when a driver stops for 15 minutes or more at a rest area or a rest area for sleepiness on a highway. In the case of FIG. 4B, passage 1 is divided from the start of driving to before entering the expressway toll gate, passage 2 is divided from entering the toll gate to a rest area where the vehicle is stopped for more than 15 minutes, and passage 3 is divided from the rest area to entering the toll gate, and passage 4 is divided into from exiting the toll gate to stopping driving on general roads. That is, in the case of FIG. 4B , the vehicle 10 may be regarded as having stopped at a rest area or a sleepy rest area. At this time, the driving score is calculated as passage 1 + passage 2 + passage 3 + passage 4.

Next, the risky driving behavior quantification unit 130 generates continuous driving time for each of the classified trips (eg, trip 1, trip 2, ,,,, trip m) (S140). The generated continuous running time has the same configuration as [Table 3].

the car's number traffic departure time arrival time continuous running time number of speeding … 69 mu 3302 passage 1 … … … … … 69 mu 3302 passage 2 … … … … … 69 mu 3302 passage 3 … … … .. .. 69 mu 3302 pass m … … … .. ..

The following [Table 4] is an example of data collected and processed in this way.

Next, the risky driving behavior quantification unit 130 calculates the entropy weight (ω _ij ) of the risky driving behavior for each of the classified passages (S160). The weight (ω _ij ) introduces the concept of entropy so that the entropy is determined according to the variance based on the size distribution of each information attribute. Therefore, the larger the probability p, the smaller the amount of information, and the smaller the probability p, the larger the amount of information. Then, entropy is calculated by calculating the average amount of information each indicator has. The entropy weight calculation procedure first organizes data in a form so that each column represents the value of the index variables, goes through a normalization process, calculates the entropy value of the normalized index, and finally calculates the entropy weight. The entropy calculation method converts the measured number of dangerous driving behaviors into the probability of occurrence (p) for each indicator, and calculates and displays the average amount of information for each indicator based on the probability of occurrence (p).

The specific calculation process is as follows. First, a matrix D and a distribution probability (pi _ij ) of the risky driving behavior index (x _ij ) are calculated according to [Equation 2] below (S162).

[Equation 2]

,

,

Here, i represents traffic from 1 to m, and j represents risky driving behavior items from 1 to n.

Then, the entropy (E _ij ) for each risky driving behavior index (x _ij ) is calculated according to the following [Equation 3] (S164).

[Equation 3]

,

,

Then, the entropy weight (ω _ij ) is calculated according to the following [Equation 4] (S166).

[Equation 4]

Entropy shows a larger value when the data is scattered and the uncertainty is high. Using this characteristic, it can be interpreted that if the distribution of risky driving behaviors occurring on the road is large, the driver's driving characteristics are diverse and has more information. In addition, the weight calculation method using entropy can be objectively analyzed by reflecting only the characteristics of quantitative data. [Table 5] is an example of such weights, and the calculated weights are stored in the weight storage unit 136.

entire
risky driving behavior entropy result weight(%) Rank Speeding 20.6 2 long-term speeding 0 6,7 rapid acceleration 20.3 4 rapid deceleration 20.4 3 sudden start 17.4 5 Sudden stop 0 6,7 continuous running time 21.2 One

Next, the risky driving behavior quantification unit 130 calculates the risky driving behavior value based on the risky driving behavior for each passage (i = 1, ..., m) and the entropy weight (ω _ij ) (S180). Specifically, the risky driving behavior value (y _i ) for each passage is calculated according to [Equation 5].

[Equation 5]

Next, the average of the calculated risky driving behavioral values (y _i ) for each passage is calculated to be the risky driving behavioral value (Y) (S184). Here, X _k is the value of dangerous driving behavior information.

Then, the server controller 110 provides the calculated dangerous driving behavior value Y to the outside (S200). Optionally, it may be converted into a safety score according to the following equation and provided.

Safety score = 1 - Dangerous driving behavior value (Y)

Detailed descriptions of the preferred embodiments of the present invention disclosed as described above are provided to enable those skilled in the art to implement and practice the present invention. Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will understand that the present invention can be variously modified and changed without departing from the scope of the present invention. For example, those skilled in the art can use each configuration described in the above-described embodiments in a way of combining each other. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The present invention can be embodied in other specific forms without departing from the spirit and essential characteristics of the present invention. Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention. The invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. In addition, claims that do not have an explicit citation relationship in the claims may be combined to form an embodiment or may be included as new claims by amendment after filing.

10: vehicle,
20: network,
100: server device,
110: server control unit,
120: communication department,
130: risk driving behavior quantification unit,
132: operation data storage unit,
134: travel data storage unit,
136: weight storage unit,
140: Dangerous driving behavior value providing unit.

Claims (10)

In the method for providing the driver's risky driving behavior value,
receiving and storing driving data from at least one vehicle 10 by the server device 100 (S100);
Classifying, by the risky driving behavior quantification unit 130, traffic of the vehicle 10 based on the driving data (S120);
Generating, by the risky driving behavior quantification unit 130, continuous driving time for each of the classified traffic (S140);
Calculating, by the risky driving behavior quantification unit 130, an entropy weight (ω _ij ) of each of the classified dangerous driving behaviors (S160);
Calculating, by the risky driving behavior quantification unit 130, a risky driving behavior value based on the risky driving behavior for each passage and the entropy weight (ω _ij ) (S180); and
A method for providing risky driving behavior values of a driver reflecting continuous driving time, comprising: providing the calculated dangerous driving behavior values to the outside by the server control unit 110 (S200). According to claim 1,
The driving data includes at least one of driving time information, vehicle driving and behavior information, GPS location information, travel rest information, and dangerous driving behavior information. According to claim 2,
The vehicle driving and behavior information includes at least one of driving distance during driving, driving time during driving, cumulative driving distance, vehicle speed, acceleration, and engine speed, and a driver's risky driving behavior value reflecting continuous driving time. How to provide. According to claim 2,
The passage pause information,
Information on the location of rest areas and sleepy shelters; and
A method for providing a driver's risky driving behavior value reflecting continuous driving time, characterized in that it includes information on whether the resting place or the drowsiness shelter is visited. According to claim 2,
The dangerous driving behavior information includes at least one of sudden stop, sudden course change, number of times of acceleration, average acceleration, average rapid acceleration, and sudden acceleration deviation. According to claim 4,
In the traffic classification step (S120),
A method for providing a driver's risky driving behavior value reflecting continuous driving time, characterized in that when the vehicle 10 visits the rest area or the sleepy rest area and passes through a toll gate on a highway, it is classified as another traffic. According to claim 1,
In the step of calculating the entropy weight (ω _ij ) (S160),
Calculating the matrix D and distribution probability p _ij of the risky driving behavior index x _ij according to the following [Equation 2] (S162);
[Equation 2]

,

calculating entropy (E _ij ) for each risky driving behavior index (x _ij ) according to the following [Equation 3] (S164); and
[Equation 3]

,

Calculating an entropy weight (ω _ij ) according to the following [Equation 4] (S166);
[Equation 4]

A method for providing risky driving behavior values of a driver reflecting continuous driving time, wherein i represents passage from 1 to m and j represents risky driving behavior items from 1 to n. According to claim 7,
In the step of calculating the risky driving behavior value (S180),
Calculating the risk exercise behavior value (y _i ) for each passage according to the following [Equation 5] (S182); and
[Equation 5]

A step (S184) of calculating the _average of the risky driving behavioral values yi for each passage to obtain the risky driving behavioral value Y,
Here, X _k is a value of risky driving behavior information. According to claim 1,
The step of providing the risky driving behavior value (S200) further includes providing a safety score according to the following equation,
Safety score = 1 - Dangerous driving behavior value
A method for providing a driver's risky driving behavior value reflecting the continuous driving time, characterized in that. According to claim 1,
In the step of providing the risky driving behavior value (S200),
providing to the vehicle;
providing evaluation of a vehicle operating on a specific road or specific area; and
providing evaluation for each vehicle divided into trucks, buses, and passenger cars; A method for providing a driver's risky driving behavior value reflecting the continuous driving time, comprising at least one of the following:

Images