KR20150126481A - System for processing and analysing big data obtaining from digital tachograph - Google Patents

Abstract

The present invention relates to a system for processing and analyzing big data using drive record data collected by a digital tachograph (DTG) terminal. Provided is a system for processing and analyzing DTG big data, comprising: a DTG big data storing part for storing raw drive record data collected by the DTG terminal; and a DTG big data processing part for refining the raw drive record data stored in the DTG big data storing part, obtaining statistical data based on the refined drive record data, and conducting mining analysis based on at least one among the refined drive record data and the obtained statistical data.

Description

TECHNICAL FIELD [0001] The present invention relates to a DTG Big Data Processing and Analysis System,

The present invention relates to a DTG big data processing and analysis system, and more particularly, to a DTG big data processing and analysis system that enables useful information to be obtained from big data on digital running records through systematic data refining and data mining procedures. .

Big data is a vast amount of data that is difficult to collect, store, and analyze with a typical database system. Examples of the big data include social data generated in a social network service, a network traffic log, a web log of a web server or an application program, sensing data and logs acquired by a sensing device, In the case of time-series data such as logs, the amount of data to be accumulated due to accumulation of data explosively increases over time.

One example of the time series data is running record data obtained by a digital tachograph or a digital tachometer (hereinafter referred to as a DTG). The DTG is a device for collecting driving record data such as the position of the vehicle, the vehicle starting, the sudden driving, the speed, etc. by the operation of the driver, and the driving record data thus obtained is provided to an administrator such as a transportation company, History management, identification of the cause of an accident in case of an accident, and accident prevention.

In accordance with the recent government policy, the installation of DTG is required to be applied to commercial vehicles such as taxis and buses, and the installation and dissemination of DTG will be expanded in the future. Due to the nature of time series data, It is necessary to construct a DTG big data processing and analysis system in order to systematically analyze a large amount of operation record data and to enable useful information obtained through analysis to be efficiently used by an administrator or a user.

The technical problem to be solved by the technical idea of the present invention is to provide DTG big data processing capable of systematically analyzing big data related to digital driving record and enabling the manager or user to efficiently utilize the result information acquired through analysis, Analysis system.

According to an aspect of the present invention, there is provided a system for performing big data processing and analysis using operation record data collected by a DTG (Digital Tachograph) terminal, the system comprising: A DTG big data storage unit for storing the record data; And refining the operation record data of the low data stored in the DTG big data storage unit to obtain statistical data based on the refinement running record data, and generating at least one of the refinement running record data and the obtained statistical data And a DTG big data processing unit for performing a mining analysis based on the DTG Big Data processing and analysis system.

In one embodiment, the driving record data includes identification data and sensing data,

Wherein the identification data includes a record of a vehicle number, a type, a vehicle registration number, a carrier registration number, and a driver identification code field of a vehicle equipped with the DTG terminal,

The sensing data may include a record of the driving distance of the vehicle equipped with the DTG terminal, the driving time, the data acquisition period, the data acquisition date and time, the speed, the engine revolutions per minute, the break signal, the position, the azimuth angle, have.

In one embodiment, the DTG big data processing unit may determine whether the record has a value within a limit range for each field of the sensing data, and if the record has a value outside the limit range, Is corrected to correspond to a value within the limit range to refine the running record data of the row data.

In one embodiment, the DTG big data processing unit detects an outlier by comparing deviations between consecutive records for each field of the sensing data, removes the detected outliers, The data can be refined again.

In one embodiment, the DTG big data processing unit detects an abnormal value by comparing records of fields correlated with each other in the sensing data, removes records detected as outliers, and rewrites the running record data of the refined low data again Can be purified.

In one embodiment, the obtained statistical data includes operational statistical data and propensity statistical data,

The running statistical data includes a record for one running distance, total running time, average speed, maximum speed, and maximum engine revolution per minute field,

The tendency statistical data includes at least one of an over speed count, a risk over speed count, a long over speed count, a rapid acceleration count, a sudden deceleration count, a quick start count, a sudden stop count, And may include a record for the number of times field.

In one embodiment, the DTG big data processing unit may statistically calculate the refinement driving record data to generate the statistical data, and determine whether the field-by-field records in the generated statistical data are repeatedly calculated within a predetermined time range And the statistical data can be obtained by correcting the record determined to be repeatedly calculated.

In one embodiment, the DTG big data processing unit classifies the driving tendency of the driver of the vehicle equipped with the DTG terminal according to the type, based on the tendency statistical data, and calculates a driving behavior degree of the driver Can be performed.

In one embodiment, the DTG big data processing unit generates exponential information indicating exponentiation of the degree of propensity of the classified type, and performs a mining process for analyzing a correlation between at least one of the fields of the propensity statistical data and the exponential information Analysis can be performed.

In one embodiment, the DTG big data processing unit may perform a mining operation for analyzing the driving tendency of the driver of the vehicle equipped with the DTG terminal, based on the refined driving record data and the obtained statistical data, Analysis can be performed.

In one embodiment, the obtained statistical data further comprises history data comprising a record for an accident history and maintenance history field,

The DTG big data processing unit may perform a mining analysis for predicting an accident risk and a maintenance time of the vehicle equipped with the DTG terminal, based on the history data, the refined driving record data, and the obtained statistical data have.

In one embodiment, the DTG big data processing unit can generate exponential information indicating exponentiation of the degree of the accident risk or the arrival of the maintenance time.

In one embodiment, the DTG big data processing section can perform mining analysis to discriminate a space where the risk of accidents is high or the air pollution is increased, based on the refined travel log data and the obtained statistical data .

In one embodiment, the DTG big data processing unit may perform mining analysis for analyzing the driving tendency of drivers according to the administrative district based on the refined driving record data and the obtained statistical data.

In one embodiment, the DTG big data processing unit generates exponential information indicating exponent of the degree of propensity of the classified type, and based on the generated exponential information, the refinement driving record data, and the obtained statistical data, A mining analysis for confirming the distribution state of the index information can be performed for each provider.

In one embodiment, the DTG big data processing unit generates exponential information indicating exponent of the degree of propensity of the classified type, and based on the generated exponential information, the refinement driving record data, and the obtained statistical data, A mining analysis may be performed to analyze the change in the driving propensity of the generated index information before and after the recognition.

In one embodiment, the DTG big data store may be configured with a distributed file system to store raw data related to the driving record.

In one embodiment, the control unit generates analysis information using the plurality of statistical data and the result information. And a user interface unit for providing the result information and the analysis information to a user,

The control unit may be configured to analyze, based on the data processed by the DTG big data processing unit, exponential analysis information on at least one of analysis information on driver's risk driving tendency, fuel efficiency index and environment improvement index, Or < / RTI >

In one embodiment, the user interface unit includes a visualization processing unit for visualizing an analysis result of the driving record data,

Wherein the visualization processing unit is configured to perform visualization on cluster analysis for each single driving record field included in the driving record data, visualization on statistical analysis for each single driving record field, visualization on scale reclassification for each driving record field At least one of visualization relating to a crosstalk analysis between two operation recording fields correlated with each other among the driving record data, visualization concerning time series raw data analysis regarding the driving record data, and visualization relating to short or long term mining analysis Can be performed.

The DTG big data processing and analysis system according to the technical idea of the present invention analyzes the big data such as collected driving record data by performing two-stage purification on raw data, , And performs a complex data mining of a short-term viewpoint and a long-term viewpoint, thereby reducing the analysis error and improving the analysis performance.

The DTG big data processing and analysis system according to the technical idea of the present invention analyzes the big data such as the collected driving record data and provides the extracted result information to the user so as to induce safe driving of the vehicle driver, , Prevent maintenance and accident prevention, improve management efficiency of transportation companies, and improve administrative areas and roads that cause accidents and environmental deterioration in public institutions.

In addition, the DTG Big Data processing and analysis system according to the technical idea of the present invention visualizes and provides the extracted information to the user, thereby allowing the manager or the user to intuitively recognize the information extracted from the big data and effectively use .

BRIEF DESCRIPTION OF THE DRAWINGS A brief description of each drawing is provided to more fully understand the drawings recited in the description of the invention.
FIG. 1 is a view for explaining a DTG big data processing and analysis system according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining the storage and management unit in the DTG big data processing and analysis system according to an embodiment of the present invention.
FIG. 3 is a flow chart for explaining a big data processing and analysis method performed in a processing unit of the DTG big data processing and analysis system according to an embodiment of the present invention, and FIGS. 4 to 10 are flowcharts And the steps of the data processing and analysis method are described in more detail.
FIG. 11 is a diagram for explaining the control unit in the DTG big data processing and analysis system according to an embodiment of the present invention.
12A and 12B are diagrams for explaining the user interface unit in the DTG big data processing and analysis system according to an embodiment of the present invention in more detail. Fig.
FIG. 14 is a view for explaining a storage format of driving record data in the DTG big data processing and analysis system according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The same reference numerals are used for the same constituent elements in the drawings, and a duplicate description thereof will be omitted.

Embodiments of the present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the invention are shown. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. The present invention is not limited to the following embodiments. Rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the invention to those skilled in the art.

In the following description of the embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. In addition, numerals (e.g., first, second, etc.) used in the description of the present invention are merely an identifier for distinguishing one component from another. Also, in this specification, when an element is referred to as being "connected" or "connected" with another element, the element may be directly connected or directly connected to the other element, It should be understood that, unless an opposite description is present, it may be connected or connected via another element in the middle.

The terminologies used herein are terms used to properly represent embodiments of the present invention, which may vary depending on the user, intent of the operator, or custom in the field to which the present invention belongs. Therefore, the definitions of these terms should be based on the contents throughout this specification. Like reference symbols in the drawings denote like elements.

FIG. 1 is a view for explaining a DTG big data processing and analysis system according to an embodiment of the present invention.

In FIG. 1, a system for processing and analyzing the big data constituted by the driving record data obtained directly through the DTG terminal is illustrated, but the technical idea of the present invention is not limited to this. For example, in the DTG big data processing and analysis system according to the technical idea of the present invention, besides the data directly obtained through the DTG terminal, big data about the operation record acquired from various sensors installed in the transportation means such as a vehicle It will be able to process it. In the following description, the DTG Big Data obtained directly through the DTG terminal is processed and analyzed for convenience of explanation.

Referring to FIG. 1, a DTG big data processing and analysis system 300 is connected to a plurality of DTG terminals 100 through a communication network 200. Here, the DTG terminal 100 is mounted on a vehicle such as a vehicle and collects and acquires operation record data from the relevant transportation means, and transmits the obtained operation record data to the DTG big data processing and analysis system 300 ). However, it is needless to say that the operation record data is transmitted to the DTG big data processing and analysis system 300 through the communication network 200 in FIG.

The driving record data acquired by the DTG terminal 100 may have a storage format as shown in Fig. However, it is needless to say that the driving record data that can be recorded according to the DTG storage format to be used may be variously modified. For example, the service record data may include coolant temperature, battery voltage, air gauge voltage, fuel gauge voltage, engine temperature, fuel level, and the like. In addition, the data acquisition cycle, the accident history, the maintenance history, and the like may be included in the driving record data.

The DTG big data processing and analysis system 300 includes a DTG big data storage and management unit 310 and a DTG big data processing unit 330. The control unit 350 includes a database 370 and a user interface Unit 390, and each component will be described in turn with reference to FIGS. 2 to 13 below.

[ DTG Big Data  Function and role of storage and management section - Fig. 2]

FIG. 2 is a diagram for explaining the storage and management unit 310 in the DTG big data processing and analysis system 300 in more detail.

Referring to FIG. 2, the storage and management unit 310 may include a management unit 311 and a data storage unit 313.

The management unit 311 can receive the running record data of raw data provided from the plurality of DTG terminals 100 (see FIG. 1) through the communication network 200 (see FIG. 1). The management unit 311 can control the operation record data storage of the low data to the data storage means 313 and the operation record data output of the low data from the data storage means 313. [

The data storage means 313 may store the running record data of the row data. The data storage means 313 may be composed of, for example, a plurality of physically separated storages, and each of the storages can share and store the same running log data of the same row data.

That is, the storage and management unit 310 may be a distributed file system such as a Hadoop distributed file system including a management unit 310 and a data storage unit 313.

[ DTG Big Data  Function and role of processing section - Fig. 3 To  10]

3 is a flowchart for explaining a big data processing and analysis method performed in the processing unit 330 of the DTG big data processing and analysis system 300, and FIGS. 4 to 10 are flowcharts of the big data processing and analysis method of FIG. These drawings are for explaining each step in more detail. Each step of the big data processing and analysis method shown in FIG. 3 can be performed in the processing unit 330 through at least one software that implements the corresponding algorithm. Hereinafter, the steps of the big data processing and analysis method shown in FIG. 3 will be described with reference to FIGS. 4 to 10. FIG.

Basic refinement process ( S3310 )

Referring to FIGS. 3 and 4, the processing unit 330 may refine the driving record data provided from the storage and management unit 310 (S3310). Here, the driving record data provided from the storage and management unit 310 may be non-refined raw data having a storage format as shown in FIG. 14, and may include identification data and sensing data.

Here, the identification data is data for identifying a vehicle equipped with the DTG terminal 100 (see Fig. 1), a driver of the vehicle, a transportation company to which the installed vehicle belongs, and the like, Code, carrier registration number, and the like. Further, the sensing data may include a record of fields such as mileage, vehicle speed, break signal, position, etc., obtained by various sensors and collected by the DTG terminal 100 DTG storage format).

The basic refining process S3310 will be described in detail. First, the processing unit 330 reads out the record data for each field from the running record data of the low data (more specifically, the sensing data included in the running record data) It is possible to detect an outlier by judging whether or not it has a value within a sensing range (i.e., a predetermined limit range) (S3311).

For example, in the case of the vehicle speed field, the processing unit 330 determines whether each record has a value within a sensing range (for example, 0 to 250 km / h) when the vehicle speed sensor operates normally, It is possible to detect a record having an outlier value as an outliers.

For example, in the case of the engine revolution per minute field, the processing unit 330 determines whether or not each record has a value within the sensing range (for example, 0 to 6000 rpm) of the engine revolution sensor per minute, Can be detected as an outlier value.

As another example, in the case of the GPS position field, the processing unit 330 determines whether each record has x and y coordinates (e.g., 125.8 <x <131.0, 33.0 <y <39.0) corresponding to longitude and latitude in the Korean territory, It is possible to detect a record having a value outside the range as an outliers.

In the case of the break signal field having the sensing values of the brake signal sensor of 0 and 1, the 0 and 1 may be set to a reference value for detecting an abnormal value, and the processing unit 330 may set the brake signal field A record having a value other than the reference value among the records can be detected as an outliers.

According to the above description, the processing unit 330 may remove or correct the records detected as outliers for each field (S3313). For example, in the vehicle speed field, the processing unit 330 determines whether the upper limit or the lower limit of the limit range and the reference deviation (for example, the sensing error range of the speed sensing device ) Can be eliminated, or a record having a deviation within the reference deviation can be corrected to a value corresponding to the upper limit or lower limit of the limit range.

Comparative purification process ( S3330 )

Referring to FIG. 3 and FIG. 5, it is possible to again compare and refine operation record data subjected to basic refinement processing (S3330).

In one embodiment, the processing unit 330 may detect an abnormal value by comparing deviations between successive records for each field in the basic refinement processed driving record data (S3331).

For example, if consecutive records in the vehicle speed field show a significant difference (the previous record is 0 km / h and the subsequent record is 100 km / h), the previous record and / can do. Similarly, in the case of the acceleration field, the engine revolution per minute field, the azimuth angle field, etc., the abnormal value can be detected by comparing the deviation of consecutive records.

In another embodiment, the processing unit 330 may compare the records of the fields correlated to each other in the basic refined transaction log data to detect an abnormal value (S3333).

For example, referring to FIGS. 6A and 6B, it is normal that the vehicle speed field and the engine speed field per minute form an inter-proportional relationship as shown in FIG. 6A (Pearson correlation coefficient is 0.89826) 6B, since the Pearson correlation coefficient is -0.79212, the processing unit 330 can detect the records forming the abnormal relationship through the record comparison of the fields correlated with each other as the outliers have.

Accordingly, the processing unit 330 can remove the records detected as abnormal values through the deviation comparison (S3331) and / or the correlation comparison (S3333) (S3335).

The data analysis reliability of the DTG big data processing and analysis system 300 can be improved through the two-step operation record data refinement.

Statistical data extraction process ( S3350 )

Referring to FIG. 3 and FIG. 7, statistical data may be obtained based on the operation history data processed by the basic tablet and the comparative refinement (S3350).

Here, the statistical data is obtained by statistically processing the refined driving record data, and may have a storage format as shown in Table 1 below.

Here, among fields of the statistical data, fields related to the driving of the vehicle equipped with the DTG terminal 100, such as a one-mileage, a total driving time, an average speed, .

In addition, a field related to the driving propensity of the driver of the vehicle equipped with the DTG terminal 100, for example, a speeding speed, a risk speeding speed, a long speeding speed, a rapid acceleration speed, The records can be classified into tendency statistical data.

Referring to FIG. 7, the statistical data acquisition process (S3350) will be described in more detail. First, the processing unit 330 may generate statistical data by statistically calculating refinement operation record data (S3351).

For example, the processing unit 330 may generate statistical data fields such as an average speed by statistically calculating (e.g., calculating an average value) the records of the vehicle speed field from the refined transaction record data.

For example, the processing unit 330 may calculate the vehicle speed field records statistically (e.g., based on the GPS position information, by limiting the speed limit of the road based on the GPS position information) And generates statistical data fields such as the number of overspeed, the number of risk overspeed, and the number of overspeed over time. Similarly, the processing unit 330 may be configured to statistically calculate the acceleration field records (for example, calculate the number of exceeding limit values in the entire section or a part of the section based on an arbitrary value) Lt; / RTI &gt;

For example, the processing unit 330 may statistically calculate (e.g., calculate an accumulation value, calculate a partial accumulation value) the driving distance and running time field records of the vehicle, and calculate statistical data such as one traveling distance, Field. &Lt; / RTI &gt;

As another example, the processing unit 330 may compute statistically the field records such as vehicle speed, azimuth angle, engine revolutions per minute, etc. (for example, an azimuth field record based on the vehicle speed field record or an engine speed field record per minute The number of times of career change, and the number of times of sharp turns.

Then, the processing unit 330 may determine whether the field record is repeatedly calculated within a predetermined time range in the plurality of generated statistical data, and may correct the record determined to be repeatedly calculated (S3353).

8, when the data acquisition cycle is 1 second, the processing unit 330 determines whether the overspeed frequency is within a predetermined time range (e.g., window) within 15 seconds, Can be calculated up to 15 times. At this time, if the driver is continuously overspeed, the record of the overspeed field should be substantially generated as 1, but it may be generated as 15, which may degrade data analysis reliability.

Accordingly, the processor 330 may determine whether the record of the overspeed field is repeatedly calculated in the window as described above, and detect an abnormal value, and correct the record of the overspeed field to one.

By such correction of the statistical data, the data analysis reliability of the DTG big data processing and analysis system 300 can be further improved.

Short-term data mining process ( S3370 )

Referring to FIGS. 3 and 9, the processing unit 330 may perform a short-term data mining analysis based on at least one of the refinement operation record data and the obtained statistical data to generate specific result information (S3370) .

Here, the data mining analysis in the short-term viewpoint may include a case in which the micro-perspective data analysis is performed on the individual DTG terminal 100 as well as the time-series analysis in the short-term perspective, that is, the real- In case of direct data related to accident / maintenance prediction such as accident history and maintenance history field, there are two methods for data mining in the short-term perspective: a regression analysis technique, a supervised learning type analysis technique, And a neural network technique may be used. In the case where there is no directly related information such as a driver's driving type, a cluster analysis technique or an association analysis technique, which is an unsupervised learning type analysis technique, may be used .

Referring to FIG. 9, the data mining process (S3370) in a short-term perspective will be described in more detail. The processing unit 330 determines the driving tendency of the vehicle driver based on the field related to the tendency in the obtained statistical data, (S3371).

In one embodiment, the processing unit 330 may include a tendency statistic that includes fields for overspeed, risk overspeed, number of long overspeed, number of sudden acceleration, number of times of sudden deceleration, number of starts, number of times ahead, number of career changes, Based on the data, the driving type of the driver can be classified into the dangerous driver, the urgent driver, the energy-consuming driver type, and the like. At this time, the non-instructional learning analysis methods exemplified above can be used as data mining techniques.

In another embodiment, the processing unit 330 may generate exponential information indicating exponents of corresponding features for each classified type (S3373).

For example, the processing unit 330 may generate exponential information indicating the degree of risk based on a field record of the number of overspeed, risk overspeed, and overspeed for the risk driver type.

For example, the processor 330 can estimate the fuel consumption and the carbon dioxide emission amount based on the field record of the number of engine revolutions per minute, the number of rapid accelerations, the number of idle revolutions per minute, and the like, The fuel consumption index information and the environmental index information can be generated by indexing.

The dangerous operation index information, the fuel efficiency index information, and the environmental index information are provided to the driver through the control unit 350 (see FIG. 1) and the user interface unit 370 (see FIG. 1) . Also, the dangerous operation index information is provided to a transportation company or the like to which the driver belongs through the control unit 350 (see FIG. 1) and the user interface unit 370 (see FIG. 1), so that the transportation company can manage, Education.

On the other hand, the processing unit 330 can estimate the accident risk and the failure risk based on the accident history and the maintenance history field included in the driving record data regardless of the classified type, and indexes the accident risk and the failure risk result, The index information and the maintenance object index information may be generated.

The accident risk index information and the failure risk index information are also provided to a driver, a transportation company, and the like in a similar manner to the dangerous operation index information, so that the driver and the transportation company can prevent the accident, So that it can be maintained.

In one embodiment, the processing unit 330 may perform mining to analyze a correlation between specific index information and specific fields of the propensity statistical data, or between specific exponential information and specific fields of the refined propulsion log data, Through this, it is possible to extract the result information indicating the mutual influence analysis result between them (S3375).

For example, the processing unit 330 may analyze the correlation between the dangerous operation index information and the field of the vehicle type or the vehicle model, and extract the result information indicating the mutual effect analysis result .

Long-term data mining process ( S3390 )

Referring to FIG. 3 and FIG. 10, the processing unit 330 may perform data mining analysis on a long-term basis using the refined operation record data, the obtained statistical data, the generated index information, etc. to generate specific result information (S3390).

Here, the long-term data mining is a concept that encompasses not only the data analysis concept of a long-term viewpoint, but also the concept of data analysis of a macro view of various DTG terminals 100.

In one embodiment, the processing unit 330 may analyze the repeated tendencies in a specific period based on the refined running record data, the obtained statistical data, and the exponential information, and extract the result information indicating the analysis result ( S3391 in Fig. 10).

For example, the processing unit 330 analyzes patterns repeated in fields of tendency statistical data of the statistical data obtained by day, time, season, or event (irregular events such as holidays, holidays, and accidents) , Result information indicating the driving behavior of the driver in a specific cycle, driving habits, and the like can be extracted. The result information may include not only the driving tendency and the driving habit in a specific period of a specific driver but also information indicating a common driving tendency and driving habits of all the drivers.

Meanwhile, the processing unit 330 correlates the dangerous operation index information, fuel efficiency index information, and the like with other information stored in the DTG big data processing and analysis system 300 or provided from external devices such as weather information and traffic information , And the result information indicating the result of the influence analysis between them may be extracted.

In another embodiment, the processing unit 330 generates a learning model for predicting a change in a specific field based on the refined running record data, the obtained statistical data, and the exponential information, and outputs a prediction result Can be extracted (S3393 in FIG. 10).

For example, the processing unit 330 may generate a learning model for predicting the occurrence timing of an accident or the like based on the accident history field, and may extract the result information indicating the accident occurrence timing and the risk, have.

For example, the processing unit 330 creates a learning model for predicting a failure occurrence timing and the like based on the maintenance history field, and extracts result information indicating maintenance period predicted with the maintenance target index information and failure risk, can do.

On the other hand, the processing unit 330 obtains a common feature from the result information indicating the occurrence timing of an accident and the risk or the occurrence timing and the danger of each DTG terminal, for example, a common accident occurrence of a specific vehicle type It is also possible to generate result information indicating the risk of an accident and the risk of failure of a specific type of vehicle through the extraction.

In another embodiment, the processing unit 330 may analyze the spatial data-related characteristics based on the refined running record data, the obtained statistical data, and the index information, and extract the result information indicating the analysis result (S3395) .

For example, the processing unit 330 may be configured to determine the location of the DTG terminal based on the GPS location field for various DTG terminals and the dangerous operation index information, fuel efficiency index information, and environmental index information for the various DTG terminals, And the resultant information indicating the over-induced roads and the like can be extracted.

Meanwhile, the processing unit 330 stores the GPS position field, the danger operation index information, the fuel consumption index information, the environmental index information, and the like of various DTG terminals in the DTG big data processing and analysis system 300 (FIG. 1) And extracts the result information indicating the exponential distribution related to the tendency of the drivers according to the administrative districts.

In another embodiment, the processing section 330 can extract the result information indicating the distribution state of the exponential information based on the specific field, based on the refinement running record data, the obtained statistical data, and the exponent information (S3397 ).

For example, the processing unit 330 analyzes the distribution status of the dangerous driving index, fuel efficiency index, and environmental index information of the drivers based on the transportation company registration number field, The result information can be extracted.

In another embodiment, the processing unit 330 may extract the result information indicating the change in the user's result information, the user's result information, and the user's result information, based on the refined operation record data, the obtained statistical data, and the index information (S3399).

For example, the processing unit 330 may be configured such that the control unit 350 provides analytical information, alarm messages, and the like generated by complex analysis of the dangerous operation index information, the fuel efficiency index information, the environmental index information, Date, date on which the driver is provided to the transportation company to which the driver belongs, and the date on which the education for the driver is performed, from the driver, the transportation company, and the like. Accordingly, the processing unit 330 confirms changes in the driving record data, the obtained statistical data, and the exponential information about the specific result information of the driver before or after the training, or before and after the driver's education, And can extract the result information indicating the analysis result.

By such complex and efficient data mining, the analysis performance of the DTG big data processing and analysis system 300 can be improved.

[Function and role of control unit - Fig. 11]

11 is a diagram for explaining the control unit 350 in the DTG big data processing and analysis system 300 in more detail. Referring to FIG. 11, the controller 350 may include an analyzer 351 and a management unit 353.

The analysis unit 351 may analyze the index information, the result information, and the plurality of statistical data generated by the processing unit 330 in a complex manner, and generate various analysis information and an alarm message reflecting the analysis result.

For example, the analyzing unit 351 can generate exponential analysis information on at least one of the analysis information on the driving tendency of each of the vehicle drivers, the fuel efficiency index and the environment improvement index, and the statistical analysis information according to the period and company. The analyzing unit 351 can generate an alarm message for providing accident risk index information and the like to the driver and the transportation company.

The analysis unit 351 can generate analysis information and an alarm message reflecting the results of analyzing the driving behavior of the drivers by the administrative districts, the accident risk of a specific road, the environmental influence, and the like.

The management unit 353 may store the analysis information, the alarm message, and the like, the statistical data, the index information, and the result information provided from the processing unit 330 in the database 370.

The management unit 353 may transmit the analysis information and the like to the driver, the transportation company, the traffic safety corporation, and the like through the user interface unit 390 in accordance with a predetermined cycle or when requested by the driver, Safe industrial complex, etc.

As a result, it is possible to induce safe driving of a driver, induce improvement of fuel mileage, induce advance maintenance and prevent accidents, improve the efficiency of the management of the transportation company, and improve the accident risk and environmental deterioration The administrative districts, roads, and the like that cause the problems.

[user Interface  Function and role - Figs. 12, 13A To  13f]

12A and FIG. 12B are diagrams for explaining the user interface unit 390 in more detail, and FIGS. 13A to 13F are views showing examples of visualization implementations provided by the user interface unit 390. FIG.

Referring to FIG. 12, the user interface unit 390 may include a visualization processing unit 391.

The visualization processing unit 391 visualizes the statistical data and the result information provided from the control unit 350 so that the user such as the driver or the transportation company can directly perceive the visualization. For example, the visualization processing unit 391 performs visualization on cluster analysis for each single driving record field included in the driving record data, visualization on statistical analysis for each single driving record field, Visualization of crosstalk between two operation record fields correlated with each other among visualization and operation record data, visualization of time series row data analysis on the operation record data, and the like can be performed.

In addition, the visualization processing unit 391 performs visualization processing, i.e., mining analysis, related to various mining analyzes in the short-term data mining process (S3370) and the long-term data mining process (S3390) The visualization process may be performed. It goes without saying that the user can perform various mining analyzes of the data mining process S3370 and the data mining process S3390 from the short-term perspective and the long-term perspective through the visualization processing of the visualization processing section 391 as described above.

13A to 13F, the visualization processing unit 391 can perform a cluster analysis on the field records such as the number of overspeed and rapid acceleration times of the vehicles in the statistical data as shown in FIG. 13A . &Lt; / RTI &gt; In addition, the visualization processing unit 391 can visualize field records such as the speed of the vehicle, the engine revolution per minute, and the like in the running record data as shown in FIG. 13B so that the cross-analysis can be performed.

13C and 13D, the visualization processing unit 391 can express the average velocity and the maximum velocity field of the statistical data as histograms, respectively. As shown in FIG. 13E, in the statistical data, It can be visualized in the form of a scatter diagram so that it can be confirmed and visualized so that the abnormal value of the time-series vehicle speed field recordings can be easily confirmed in the running record data as shown in FIG. 13F.

In this way, the DTG big data processing and analysis system 300 visualizes the extracted information through the user interface unit 390 and provides it to the user so that the user can intuitively recognize the information extracted from the big data And can also be used for direct mining analysis.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, This is possible.

100: DTG terminal
200: Network
300: DTG Big Data Processing and Analysis System

Claims (19)

A system for performing a big data processing and analysis using driving record data collected by a DTG (Digital Tachograph) terminal,
A DTG big data storage unit for storing driving record data of raw data collected by the DTG terminal; And
Wherein the control unit is configured to refine the operation record data of the low data stored in the DTG big data storage unit to obtain statistical data based on the refinement operation record data and to store at least one of the refinement operation record data and the obtained statistical data A DTG big data processing unit for performing a mining analysis based on the DTG large data processing unit;
DTG Big Data Processing and Analysis System.
The method according to claim 1,
Wherein the driving record data includes identification data and sensing data,
Wherein the identification data includes a record of a vehicle number, a type, a vehicle registration number, a carrier registration number, and a driver identification code field of a vehicle equipped with the DTG terminal,
Wherein the sensing data includes a record of a driving distance of the vehicle equipped with the DTG terminal, a driving time, a data acquisition period, a data acquisition date and time, a speed, an engine revolution speed per minute, a brake signal, a position, DTG Big Data Processing and Analysis System.
3. The method of claim 2,
Wherein the DTG big data processing unit determines whether the record has a value within a limit range for each field of the sensing data and if the record has a value outside the limit range, And correcting the running record data of the low data.
The method of claim 3,
The DTG big data processing unit detects an outlier by comparing deviations between consecutive records in each field of the sensing data and removes the detected outliers to refine the driving record data of the already-processed low data , DTG Big Data Processing and Analysis System.
The method of claim 3,
The DTG big data processing unit detects the abnormal value by comparing the records of the fields correlated with each other in the sensing data and removes the record detected as the abnormal value to refine the running record data of the refined low data. Data processing and analysis system.
The method according to claim 1,
The obtained statistical data includes operational statistical data and propensity statistical data,
The running statistical data includes a record for one running distance, total running time, average speed, maximum speed, and maximum engine revolution per minute field,
The tendency statistical data includes at least one of an over speed count, a risk over speed count, a long over speed count, a rapid acceleration count, a sudden deceleration count, a quick start count, a sudden stop count, A DTG Big Data Processing and Analysis System, comprising a record for a number of fields.
The method according to claim 6,
The DTG big data processing unit statistically calculates the corrected driving record data to generate the statistical data, judges whether the field-by-field records in the generated statistical data are repeatedly calculated within a predetermined time range, And acquiring the statistical data by correcting the record determined to be calculated.
The method according to claim 6,
The DTG big data processing unit may classify the driving tendency of the driver of the vehicle equipped with the DTG terminal on the basis of the tendency statistical data and classify the degree of driving propensity of the driver for each of the classified types, DTG Big Data Processing and Analysis System to perform analysis.
9. The method of claim 8,
Wherein the DTG big data processing unit performs a mining analysis for analyzing a correlation between at least one of the fields of the tendency statistical data and the index information, DTG Big Data Processing and Analysis System.
The method according to claim 6,
Wherein the DTG big data processing unit performs a mining analysis for analyzing an operation propensity of a driver of a vehicle equipped with the DTG terminal on the basis of a specific period based on the refinement driving record data and the obtained statistical data, DTG Big Data Processing and Analysis System.
The method according to claim 6,
Wherein the obtained statistical data further includes history data including a record of an accident history and maintenance history field,
Wherein the DTG big data processing unit performs a mining analysis for predicting an accident risk and a maintenance time of a vehicle equipped with the DTG terminal, based on the history data, the refined driving record data, DTG Big Data Processing and Analysis System.
12. The method of claim 11,
And the DTG big data processing unit generates exponential information indicating exponentiation of the degree of the accident risk or the arrival of the maintenance time.
The method according to claim 6,
The DTG big data processing unit may be configured to perform DTG Big Data processing and analysis to perform mining analysis to discriminate a space where the risk of an accident is high or air pollution is increased based on the refinement operation record data and the obtained statistical data system.
The method according to claim 6,
Wherein the DTG big data processing unit performs mining analysis for analyzing driving behavior of drivers according to the administrative area based on the refined driving record data and the obtained statistical data.
9. The method of claim 8,
The DTG big data processing unit generates exponential information indicating exponent of the degree of propensity of the classified type and generates index information for each transportation carrier on the basis of the generated exponential information, the refinement running record data, The DTG Big Data Processing and Analysis System performs mining analysis to check the distribution status of DTG.
9. The method of claim 8,
Wherein the DTG big data processing unit generates exponential information indicating exponent of the degree of propensity of the classified type, and based on the generated exponential information, the refinement driving record data, and the obtained statistical data, A DTG Big Data Processing and Analysis System that performs mining analysis to analyze the change of driving propensity before and after recognition of information.
The method according to claim 1,
Wherein the DTG big data storage is configured with a distributed file system to store raw data related to the driving record.
The method according to claim 1,
A control unit for generating analysis information using the plurality of statistical data and the result information; And a user interface unit for providing the result information and the analysis information to a user,
The control unit may be configured to analyze, based on the data processed by the DTG big data processing unit, exponential analysis information on at least one of analysis information on driver's risk driving tendency, fuel efficiency index and environment improvement index, , &Lt; / RTI &gt;
19. The method of claim 18,
Wherein the user interface unit includes a visualization processing unit for visualizing an analysis result of the driving record data,
Wherein the visualization processor is configured to perform visualization on cluster analysis for each single driving record field included in the driving record data, visualization on statistical analysis for each single driving record field, visualization on scale reclassification for each driving record field, At least one of visualization relating to crosstalk between two operation recording fields correlated with each other among the driving record data, visualization concerning time series raw data analysis regarding the driving record data, and visualization relating to short or long term mining analysis DTG Big Data Processing and Analysis System.

Images