KR102295427B1 - System and method for detecting status of vehicle based on data collected by obd - Google Patents

Abstract

According to the present invention, the vehicle abnormal state detection system based on data collected through an On Board Diagnostics (OBD) device includes a server and a user terminal, and the user terminal is mounted on each vehicle registration information and each vehicle. Collects vehicle data including data collected through the OBD device and GPS information of each user terminal, removes abnormal data values from the vehicle data and filters so that normal data values remain, and the server includes a plurality of users Receive the normal data value and the abnormal data value from the terminal, and based on the filtered normal data value, the vehicle's cargo transport safety, vehicle history management information, depreciation cost of the vehicle, and whether abnormal conditions occur by vehicle model is determined and provided to the user terminal or other server, and by using the abnormal data values, it is determined whether the OBD device malfunctions, communication status is defective, vehicle defect is present, and driving operation error occurs, and the user terminal or other server can be provided as

Description

SYSTEM AND METHOD FOR DETECTING STATUS OF VEHICLE BASED ON DATA COLLECTED BY OBD}

The present invention relates to a method and system for detecting a vehicle state based on data collected through an On Board Diagnostics (OBD) device. Specifically, it is a technology for realizing car management or traffic safety prediction through big data analysis after analyzing car data collected from OBD devices in a smartphone app and transmitting it to a server.

In the related art, data generated from the vehicle is collected by connecting a vehicle electronic tachograph (Digital Tachograph) in the form of hardware to communication of the vehicle through wiring.

In addition, the vehicle owner or driver provides monitoring of the vehicle to enable easy management. .

On the other hand, the vehicle electronic driving recorder is very expensive, it is necessary to pay a high cost for installation, and there are many problems of data omission due to frequent breakdowns.

Therefore, there is a need to reduce the high cost of installation and use by providing means that can replace the electronic driving recorder for automobiles. In addition, from a macroscopic point of view, in order to implement traffic safety by easily collecting overall traffic information and vehicle information from public entities such as the Transportation Safety Authority, a means for easily collecting and monitoring each vehicle information is also required.

The present invention is to solve the problems of the prior art described above, by connecting an OBD device mounted on a conventional vehicle and a smart phone to easily collect vehicle information to a user terminal, and transmit it to a server to perform big data analysis on the server By making it happen, it is intended to make predictions for overall traffic safety or management of vehicles easy.

In the method of detecting a vehicle state based on data collected through an On Board Diagnostics (OBD) device, performed by a server, according to an embodiment of the present invention, (a) each user terminal, each vehicle registration information , collecting data collected through an OBD device mounted on each vehicle, and vehicle data including GPS information of each user terminal; (b) filtering, by each user terminal, to remove an abnormal data value from the vehicle data and leave a normal data value; (c) receiving the normal data value and the abnormal data value from a plurality of user terminals, and Based on the filtered normal data value, the vehicle cargo transport safety, vehicle history management information, depreciation cost of the vehicle, and determining whether an abnormal condition occurs for each vehicle model and providing the determination to the user terminal; and (d) determining whether the OBD device malfunctions, communication state failure, vehicle defect, and driving operation error using the abnormal data values, and providing it to a user terminal or other server. can

In addition, the user terminal may be installed with an application capable of performing the steps (a) to (d) in communication with the server and the OBD device.

In addition, the step (a) is defined for each vehicle registration information, each vehicle state information, and each vehicle location information, and the number of digits of data that can be recognized for each information, a data convention defining what appears as a number when converted into structured data, and a preset table value in which a data generation time is defined is stored in the user terminal, and converting data received from the OBD device according to a standard for each item with reference to the table value.

Also, in step (b), the abnormal data value is the latitude and longitude coordinates of the GPS when the one mileage of the vehicle is calculated as negative, when the one mileage of the vehicle is calculated as four digits or more, the latitude and longitude coordinates of the Republic of Korea and a data value in the case where the vehicle speed value is negative when calculated to deviate by a preset distance from the longitude, and is calculated as the RPM exceeding five digits.

In addition, the step of determining the safety of cargo transport of the vehicle in step (c) includes collecting vehicle speed, acceleration, and direction values in real time to determine whether the vehicle is a speeding type, a rapid acceleration type, a rapid deceleration type, or a sudden lane. Statistics are collected on a daily basis for any type of change, sudden turn, and continuous driving, and the average value of the speed, acceleration, and direction values of the vehicle during the same period as the speed, acceleration, and direction values of the vehicle and the The method may include determining cargo transport safety by comparing average values according to the types of vehicles, and providing them to a user terminal of a driver of the vehicle.

In addition, in the step of determining the depreciation cost of the vehicle in step (c), the data collected in step (a) is stored as time-series statistical data for each type of vehicle, and the depreciation cost is calculated for each vehicle model. Prediction, but based on the statistical data, the number of times for overspeed, rapid acceleration, rapid deceleration, sudden lane change, and sudden turn. Operating threshold value for at least one of speed, acceleration, direction value, coolant temperature, engine oil temperature, and intake air temperature can be provided to the user terminal by calculating the difference between the number of occurrences of each vehicle and the occurrence of excess, predicting the depreciation cost, and comparing it with a preset statistical depreciation cost.

In addition, in the step (c) of determining whether an abnormal condition has occurred for each vehicle model, a plurality of state data of a vehicle to which the registered vehicle identification number and manufacturer information of the OBD device being used by the user are mapped is collected from an external server. Then, the collected data is stored for each vehicle, the data is classified by condition information item, and big data analysis is performed, the correlation between the normal data value and the abnormal data value is analyzed for each vehicle, and the correlation between the condition information items By analyzing the relationship, it may include detecting the presence or absence of an abnormal state according to the vehicle model.

In addition, (e) by storing the abnormal data values by category, and performing big data analysis on how much the abnormal data values deviate from the threshold corresponding to the normal distribution and the number of abnormal data values that are deviated, the vehicle model, the year of manufacture, and the abnormal data value Analyzing the correlation between the categories, the category includes the vehicle identification number and the year of vehicle manufacture, and inferred whether the configuration of each abnormal data value means OBD device malfunction, poor communication, vehicle defect, or driver's operation error. Then, the OBD device malfunction, communication state failure, vehicle defect, and driver's operation error are set as output values, and machine learning is performed by setting the vehicle model, year of manufacture, and abnormal data values as input values, and then, new abnormalities are set as output values. When the data value is received, the method may include detecting which state the vehicle represents among OBD device malfunction, communication state failure, vehicle defect, and driver's operation error, and guiding the vehicle to a user terminal.

In addition, according to another embodiment of the present invention, the vehicle abnormal state detection system based on data collected through an On Board Diagnostics (OBD) device includes a server and a user terminal, wherein the user terminal includes each vehicle registration information , collects vehicle data including data collected through the OBD device mounted on each vehicle and GPS information of each user terminal, removes abnormal data values from the vehicle data, and filters so that normal data values remain, the The server receives the normal data value and the abnormal data value from a plurality of user terminals, and based on the filtered normal data value, cargo transportation safety of the vehicle, vehicle history management information, depreciation cost of the vehicle, and the vehicle It determines whether an abnormal condition has occurred for each model and provides it to the user terminal or other server, and uses the above abnormal data values to determine whether the OBD device malfunctions, communication status, vehicle defect, and driving operation error. , may be provided to a user terminal or another server.

The present invention connects an OBD device mounted on a conventional vehicle and a smart phone to easily collect vehicle information to a user terminal and transmits it to a server so that big data analysis is performed on the server, thereby predicting for overall traffic safety, Vehicle management can be easily accomplished.

It is possible to collect vehicle driving record data without separately purchasing expensive equipment.

In addition, real-time transmission of data collected through the driver's smartphone is possible without using a separate communication module.

Since vehicle driving record data can be transmitted to both public and private servers set by the vehicle owner, the range of data utilization can be greatly increased by the public and private parties.

1 is a structural diagram of a system according to an embodiment of the present invention.
2 is a block diagram illustrating an example of prediction and analysis information according to an embodiment of the present invention.
3 is a structural diagram of a server according to an embodiment of the present invention.
4 is a flowchart of a vehicle state detection method according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, this means that other components may be further included, rather than excluding other components, unless otherwise stated.

The "user terminal" referred to below may be implemented as a computer or portable terminal that can access a server or other terminal through a network. Here, the computer is, for example, a laptop, desktop, laptop, VR HMD (eg, HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.) equipped with a web browser (WEB Browser), etc. may include. Here, VR HMD is for PC (eg, HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), for mobile (eg, GearVR, DayDream, Storm Horse, Google Cardboard, etc.) Independently implemented Stand Alone models (eg Deepon, PICO, etc.) are included. A portable terminal is, for example, a wireless communication device that guarantees portability and mobility, and includes not only a smart phone, a tablet PC, a wearable device, but also Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, and ultrasound (Ultrasonic). , infrared, Wi-Fi, Li-Fi, etc. may include various devices equipped with a communication module. In addition, the "network" refers to a connection structure capable of exchanging information between each node, such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), and the Internet. (WWW: World Wide Web), wired and wireless data networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, infrared communication, ultrasound Communication, Visible Light Communication (VLC), LiFi, etc. are included, but are not limited thereto.

Here, the OBD device means a self-diagnostic connector mounted inside a vehicle to check the vehicle state, and the OBD connector is provided on the dashboard side of the front of the center fascia of the vehicle. These OBD devices can monitor various parts of the vehicle and collect various data. Coolant temperature, engine oil temperature, automatic transmission oil temperature, intake air temperature, intake air volume, TPS, ISA, oxygen sensor, ignition angle and fuel injection amount, air-fuel ratio learning amount, etc. can be measured.

Referring to FIG. 1 , a system according to an embodiment of the present invention may include a server 100 , a user terminal 200 , an OBD device 210 of a vehicle, and a communication network 300 .

The server 100 is a server 100 owned by various public and private entities, and although only one is shown in the drawing, a plurality of servers 100 owned by each public and private entity may exist.

The OBD device can collect driving information and status information of the vehicle, and is a device installed inside the vehicle.

The user terminal 200 may be a driver of a vehicle or a smart phone or tablet PC or other portable terminal owned by the owner of the vehicle. The user terminal 200 communicates with the server 100 and the OBD device, and after data collection, data conversion and filtering, an application implemented to be transmitted to the server 100 may be installed.

The information collected from the OBD device is wirelessly transmitted to the user terminal 200 , and the user terminal 200 may transmit the collected information to the server 100 through the communication network 300 in real time.

The server 100 may derive and store various pieces of information through big data analysis based on the collected data.

Illustratively, referring to FIG. 2 , the server 100 provides information on cargo transport safety, information on vehicle history management, information on abnormal conditions for each vehicle model, information on vehicle depreciation, and OBD device 210 . It is possible to derive and store information on whether or not there is a malfunction of the vehicle, information on whether communication is defective, information on whether there is an error in driving operation, and information on whether or not there is a vehicle defect.

In addition, the server 100 may send the stored information to the user terminal 200 so that the vehicle owner or driver can help the vehicle management or safe driving. The information can be used in areas related to traffic safety or various vehicle management.

Referring to FIG. 3 , the server 100 may include a DB, a processor, a memory, and a communication module.

The DB may store various vehicle-related information collected from the user terminal 200 .

The memory may store a program capable of performing big data analysis based on vehicle information collection according to an embodiment of the present invention.

The processor may be implemented to derive various pieces of information shown in FIG. 2 by executing a program (or application) stored in the memory.

The communication module may exchange an interaction with the user terminal 200 through the communication network 300 , and may receive vehicle information collected by the user terminal 200 .

Hereinafter, with reference to FIG. 4 , a method for detecting a vehicle state based on data collected through the OBD device 210 performed by the system according to an embodiment of the present invention will be described in detail.

First, the user terminal 200 performs connection (pairing) with the OBD device 210 of the vehicle.

The user terminal 200 may collect vehicle data from the OBD device 210 .

The user terminal 200 may filter the collected vehicle data into valid data (S110). Specifically, the user terminal 200 may determine and filter abnormal data so that only normal data remain.

First, the user terminal 200 may convert data collected through OBD, data on vehicle information, and data collected from GPS of the user terminal 200 according to standards for each data item. Specifically, the user terminal 200 is defined for each vehicle registration information, each vehicle state information, and each vehicle location information, and the number of digits of data that can be recognized for each information, a data convention that defines what appears as a number when converted to structured data, and based on a preset table value in which the data generation time is defined, the conversion may be performed. For example, as shown in Table 1-3 below, each data can be converted according to the data protocol set for each item. However, the table below is only an example and may be converted to other conventions or forms.

Data classification data item digit Data convention (structured data conversion) Data generation time vehicle registration information vehicle identification number 17 Settings (required when downloading the app for the first time) car type 2 10: bus
17: Special passenger car
21: general taxi
31: truck
41: non-commercial vehicle Settings (required when downloading the app for the first time) Vehicle registration number 12 Mark all vehicle registration numbers Settings (required when downloading the app for the first time) Transport business registration number (for business use) 10 Mark all business registration numbers Settings (required when downloading the app for the first time) driver code 18/12 Driver's license number, blank #, omit the middle '-', driver's license number is 10 digits Settings (required when downloading the app for the first time)

Data classification data item digit Data convention (structured data conversion) Data generation time Vehicle Condition Information (OBD) Daily mileage (km) 4 Distance traveled from 00:00 to 24:00 real time Accumulated mileage (km) 7 Accumulated distance from the date of initial setting real time Date and time of information 14 YYMMDDhhmmssss
(Year/Month/Day/Hour/Minute/0.01 Second) real time Engine revolutions per minute (RPM) 4 Range: 0000 to 9999 real time brake signal One 0(off), 1(on) real time gear number real time coolant temperature 2 Range: 00~99 real time engine oil temperature 2 Range: 00~99 real time automatic transmission oil temperature 2 Range: 00~99 real time intake air temperature 2 Range: 00~99 real time TPS (Throutle Position Sensor) Before data modeling real time Idle Speed Actuator (ISA) Before data modeling real time oxygen sensor Before data modeling real time Inversion angle and fuel injection amount Before data modeling real time Performance cost learning amount Before data modeling real time

Data classification data item digit Data convention (structured data conversion) Data generation time Vehicle location information (smart device GPS) Vehicle speed (km/h) 3 000~255 real time X-axis value of latitude and longitude coordinates of GPS satellite navigation system 9 notation in decimal
(Example: 127.123456*1000000 =>127123456) real time Y-axis value of latitude and longitude coordinates of GPS satellite navigation system 9 real time GPS (Satellite Navigation System) azimuth 3 Range: 0~360
real time x-axis acceleration 6 Range: -100.0 to +100.0 real time acceleration in the y-axis direction 6 real time

The data converted in this way is defined as a number, so calculation is possible. As a result, it can be seen that big data analysis is possible.

Thereafter, the user terminal 200 determines an abnormal data value. For example, if one mileage is negative, the one mileage is determined as an abnormal data value because the lowest value of a vehicle that has not been driven all day is 0, and a negative value cannot be obtained. Considering the current vehicle speed and traffic conditions, driving more than 2,000 km per day is also a distance that is practically impossible even if the driver is replaced, so it is determined as an abnormal data value. If the latitude and longitude coordinates of the GPS location data are 00, respectively, and do not exist as the latitude and longitude coordinates of a vehicle operating in Korea, it is determined as an abnormal data value. In addition, there are date errors such as negative speed values, temperatures exceeding 100 degrees, rpm exceeding 10,000, December 1, 1970 or 25 minutes 61 seconds, and unreadable data occurs, so these are all abnormal data values. to be determined as On the other hand, since the data rules stipulated in Tables 1 to 3 are set to exclude data values that cannot be generated based on scientific knowledge, it can also be seen that a predetermined filtering action is performed even in the process of data conversion.

Thereafter, the server 100 may receive vehicle registration information, OBD collection data, and GPS information from the user terminal 200 (S120). In this case, the user terminal 200 may select a server 100 to transmit data and transmit data to at least one server 100 among the institution server 100 , the enterprise server 100 , and the user server 100 .

The server 100 may perform big data analysis and machine learning techniques on the filtered data to generate statistics and predictive data on the vehicle state, and may provide it to the server 100 manager terminal or the user terminal 200 ( S130).

The more data transmitted to the server 100, specifically, the more vehicles, the easier it is to analyze the cause of data close to the actual value and data that is recognized as an error. Big data processing technology is inevitably required for this data analysis. There are, however, two aspects. IoT data continues to be produced from embedded or attached sensors throughout the lifetime of the original device. Since a large amount of data is also generated during the driving time of the IoT data of the vehicle, it is inevitable to consider the real-time, which enables users to quickly access the results through rapid processing, and the cost of communicating large amounts of data. That is the economic aspect.

Machine learning among artificial intelligence technologies can be used for big data analysis. Data of individual vehicles stored in the app of each user terminal 200 can be transmitted to the server 100 and the result values of all vehicles analyzed and big data of vehicles corresponding to a specific category can be digitized and provided. Through this, it is possible to see in real time the difference between the data of individual vehicles as well as the operating threshold, which is a reference value related to traffic or vehicle safety/management. That is, according to the present invention, only data of individual vehicles is analyzed, and analysis results of individual vehicles are provided to the user to facilitate vehicle condition monitoring or management. In addition, as the data of individual vehicles are collected and the analysis of the entire vehicle is compared and analyzed with the data of individual vehicles through the results, a statistical approach and solution based on the arbitrarily assigned reference value (operating threshold) are derived from actual data. can make this possible.

The server 100 determines, based on the filtered normal data value, the safety of cargo transportation of the vehicle, vehicle history management information, the depreciation cost of the vehicle, and the occurrence of abnormal conditions for each vehicle model, and provides it to the user terminal 200 . can do.

In the process of judging the safety of cargo transportation of a vehicle, the speed, acceleration, and direction values of the vehicle are collected in real time and the corresponding vehicle is set to overspeed type, rapid acceleration type, rapid deceleration type, abrupt lane change type and sudden turn type, non-stop continuous By collecting statistics on a daily basis for any type of driving, and comparing the speed, acceleration, and direction values of the vehicle with the average value of the speed, acceleration, and direction values of all vehicles during the same period with the average value according to the type of vehicle, , it is possible to judge the safety of cargo transportation. And, it may be provided to the user terminal 200 of the driver of the vehicle.

During the above process, for example, the driving type of the vehicle may be determined with reference to the criteria shown in Table 4 below. The numerical values in Table 4 below are only an example and do not limit the scope of the present invention.

division truck standard speeding type 1. speeding In case of exceeding the road speed limit by 20 km/h 2. Long-term speeding Exceeding the road speed limit by 20 km/h
When driving for more than 3 minutes Rapid acceleration type 3. Rapid acceleration At speeds above 6.0 km/h
When driving at an acceleration of 5 km/h or more per second 4. Rapid departure Starting at a speed of 5.0 km/h or less
When driving at an acceleration of more than 6 km/h per second Rapid deceleration type 5. Rapid deceleration Decelerates more than 8 km/h per second
When the speed is 6.0 km/h or higher 6. Sudden stop Decelerate more than 8 km/h per second
When the speed becomes 5.0 km/h or less Type of lane change
(revolutions per second) 7. Change of radical route When the speed is 30 km/h or more, the direction
Change the vehicle to left/right 6°/sec or more,
Accumulated angle is less than ±2°/sec for 5 seconds,
When acceleration/deceleration is less than ±2km/h per second 8. Fast ahead When the speed is 30 km/h or more, the direction
Change the vehicle to left/right 6°/sec or more,
Accumulated angle is less than ±2°/sec for 5 seconds,
If the acceleration is more than 3 km/h per second Rapid rotation type
(cumulative rotation angle) 9. Turn left and right
(60~120˚) The speed is more than 20 km/h,
Left/Right within 4 seconds (accumulated rotation angle
60~120˚ range) 10.Class U-turn
(160~180˚) The speed is 15 km/h or more,
Left or right in 8 seconds
(160~180˚ range) 11.Continuous operation When the operating time is 4 hours or more and there is a break of 15 minutes or less

In addition, the server 100 calculates the number of times each vehicle deviates from the standard value for each item and the corresponding data value by statistics such as daily and monthly according to the criteria in Table 4 above for each vehicle, and calculates the average value of all vehicles and vehicle classification (passengers, freight cars, vans) etc.) and can be quantified by comparing with the average value according to the

Thereafter, the server 100 compares and shows whether each vehicle is safely operated with the entire vehicle through big data analysis for each vehicle and vehicle type, thereby increasing the awareness of safe operation to the driver of a vehicle carrying cargo. can In addition, cargo transportation enables the management of accident-free and safe transportation by tracking real-time operation records for the shipper who placed the order.

Also, the server 100 may determine whether the vehicle carrying the cargo arrives on time. Based on the vehicle's GPS information, it is possible to track the vehicle's location and estimate its moving trajectory. In this case, if the destination of the vehicle is known, the optimal route setting may be recommended to the user terminal 200 of the vehicle owner. Furthermore, according to the results of the analyzed location tracking and movement trajectory analysis, the arrival time of the corresponding freight vehicle is predicted, and if it arrives on time, it arrives on time, and if it arrives over time, it analyzes the difference between the predicted time and the exceeding time. It can be shown by the terminal 200 .

In addition, the server 100 may provide a standardized transport manual by comparing and analyzing the required time for transporting cargo between drivers. For example, by referring to the departure point and destination of vehicle drivers, information on the freight transport time required is collected, each information is compared with each other, and compared to the departure point and destination, the recommended movement route may be provided as a manual.

In addition, the server 100 may calculate the depreciation cost of the vehicle and provide it to the user terminal 200 .

Specifically, in the process of determining the depreciation cost of the vehicle, the normal data collected and filtered by the user terminal 200 is stored as time-series statistical data for each type of vehicle. Next, the server 100 predicts the depreciation cost for each vehicle model, but based on the statistical data, the number of times related to overspeed, rapid acceleration, rapid deceleration, sudden lane change, and sudden turn speed, acceleration, direction value and coolant temperature , engine oil temperature, and intake air temperature by calculating the difference between the number of occurrences of each vehicle exceeding the operating threshold for at least one of the engine oil temperature and the intake air temperature and the occurrence of the excess, it is possible to predict the depreciation cost. And, the server 100 may compare the preset statistical depreciation cost with the predicted depreciation cost, and provide it to the user terminal 200 .

In addition, the server 100 may determine whether an abnormal state has occurred for each vehicle model.

Specifically, the process of determining whether an abnormal condition has occurred for each vehicle model is a pre-registered vehicle identification number (a vehicle-specific serial number given to a vehicle by the manufacturer, consisting of a total of 17 numbers and alphabets. The vehicle number can be changed, but the chassis number is Since the number does not change, it is possible to collect a plurality of state data of the vehicle to which the vehicle theft prevention and manufacturer defect tracking) and the manufacturer information of the OBD device being used by the user are mapped from the external server 100 can be collected preferentially. have. Then, the server 100 stores the collected data for each vehicle, classifies the data by status information item, and performs big data analysis. Thereafter, the server 100 may detect the presence or absence of an abnormal state according to the vehicle model by analyzing the correlation between the normal data value and the abnormal data value for each vehicle and analyzing the correlation between the state information items. Through the correlation analysis between these data items, it is possible to quickly and clearly grasp the abnormal state according to the vehicle model.

In addition, the server 100 may use the abnormal data values to determine whether an OBD device malfunctions, a communication state failure, a vehicle defect, and a driving operation error occur, and provide it to the user terminal 200 . .

Specifically, the server 100 stores the abnormal data values by category, and performs big data analysis on how much the abnormal data values deviate from the threshold corresponding to the normal distribution and the number of abnormal data values that deviate, so that the vehicle model and year of manufacture Analyze the correlation between and abnormal data values. In this case, the category may include a vehicle identification number and a vehicle manufacturing year. Thereafter, the server 100 may infer whether the configuration of each abnormal data value means a malfunction of the OBD device 210 , a poor communication state, a vehicle defect, or a driver's operation error. The server 100 sets the OBD device 210 malfunction, communication state failure, vehicle defect, and driver's operation error as output values, and sets the vehicle model, year of manufacture, and abnormal data values as input values to set a preset machine learning algorithm. machine learning can be performed accordingly. When the learning model is completed according to this process, the server 100 thereafter, when a new abnormal data value is received, input the new abnormal data value, the corresponding vehicle model, and the manufacturing year as INPUT, and the corresponding vehicle is OBD It is possible to detect which state of the device 210 malfunction, communication state failure, vehicle defect, and driver's operation error is indicated.

Thereafter, the server 100 may provide the analyzed information to the user terminal 200 , may transmit it to the manager terminal of the server 100 , or may transmit it to another public/private server 100 .

If the above-analyzed information is collected by the Transportation Safety Authority (driving record analysis system) of the Ministry of Land, Infrastructure and Transport, basic data for establishing a traffic safety policy is provided to traffic administrative agencies, and traffic accident investigation basis data, traffic It has the advantage of realizing traffic safety by providing improvement data for accident-prone areas, transport company management and inspection data, and various statistical data to related organizations, transport companies, and transport business managers.

In addition, when the analysis-completed information is collected by the logistics company, data on the safe transportation of the cargo can be provided to the shipper who has requested the cargo transportation and used to manage the belonging transportation vehicle. In addition, the driver's driving pattern can be identified and used as basic information for contracts for individual vehicles.

In addition, when the analysis-completed information is collected by the distribution company, it can be used to respond to customer needs through real-time location tracking of the transported cargo and to manage the belonging transport vehicle. In addition, by accumulating information on the driving patterns of drivers who are members of the company, it can be used for driver education and prevention of accidents in advance.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Although the methods and systems of the present invention have been described with reference to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

100: server
200: user terminal
210: OBD device
300: communication network (network)

Claims (9)

In the method of detecting the vehicle condition based on data collected through an On Board Diagnostics (OBD) device, which is performed by a server,
(a) collecting, by each user terminal, vehicle data including each vehicle registration information, data collected through an OBD device mounted on each vehicle, and GPS information of each user terminal;
(b) filtering, by each user terminal, to remove abnormal data values from the vehicle data and to leave normal data values;
(c) receiving the normal data value and the abnormal data value from a plurality of user terminals, and based on the filtered normal data value, cargo transport safety of the vehicle, vehicle history management information, depreciation cost of the vehicle, and the vehicle determining whether an abnormal state has occurred for each model and providing it to a user terminal; and
(d) using the abnormal data values to determine whether the OBD device malfunctions, communication state failure, vehicle defect, and driving operation error occurrence, and provide it to a user terminal or other server; and
In step (c), determining whether or not an abnormal state occurs for each vehicle model is to collect a plurality of state data of the vehicle to which the registered vehicle identification number and the manufacturer information of the OBD device being used by the user are mapped from an external server, The collected data is stored for each vehicle, the data is classified by condition information item, and big data analysis is performed, the correlation between the normal data value and the abnormal data value is analyzed for each vehicle, and the correlation between the condition information items is analyzed. by analyzing, detecting the presence or absence of an abnormal condition according to the vehicle model. The method of claim 1,
In the user terminal, an application capable of performing the steps (a) to (d) in communication with the server and the OBD device is installed, the method. The method of claim 1,
The step (a) is,
It is defined for each vehicle registration information, vehicle status information, and vehicle location information, and a data convention that defines the number of digits of data that can be recognized for each information, what numbers appear when converted to structured data, and a data generation time point are defined. Table values are stored in the user terminal,
and converting the data received from the OBD device according to a standard for each item with reference to the table value. The method of claim 1,
Step (b) is,
The abnormal data value is such that when the one mileage of the vehicle is calculated as negative, when the one mileage of the vehicle is calculated as four or more digits, the latitude and longitude coordinates of the GPS deviate by a preset distance from the latitude and longitude of the Republic of Korea. When it is calculated, when the speed value of the vehicle is negative, the method includes a data value in the case of calculating an RPM that exceeds a five-digit number. The method of claim 1,
The step of determining the cargo transport safety of the vehicle in step (c) is,
By collecting vehicle speed, acceleration, and direction values in real time, statistics are collected on a daily basis whether the vehicle is a speeding type, a rapid acceleration type, a rapid deceleration type, a sudden lane change type, a sudden turn type, or a continuous driving type. And, by comparing the speed, acceleration, and direction values of the vehicle and the average values of the speed, acceleration, and direction values of the entire vehicle during the same period with the average value according to the type of vehicle, the safety of cargo transportation is determined, and the A method comprising providing to the driver's user terminal. The method of claim 1,
The step of determining the depreciation cost of the vehicle in step (c),
Store the data collected in step (a) as time-series statistical data for each type of vehicle,
For each vehicle model, predict the depreciation cost, but based on the statistical data, speed, acceleration, direction values and coolant temperature, engine oil temperature, intake air Predict the depreciation cost by calculating the difference between the number of times each vehicle exceeds the operating threshold for at least one of the temperatures and the occurrence of the excess;
Compared with the preset statistical depreciation cost, the method of providing to the user terminal. delete 5. The method of claim 4,
(e) the correlation between the vehicle model, the year of manufacture, and the abnormal data value by storing the abnormal data value by category, and performing big data analysis on how much it deviates from the threshold corresponding to the normal distribution and the number of abnormal data values that deviate Analyze the relationship, but the category includes the vehicle identification number and the vehicle manufacturing year,
After inferring what the configuration of each abnormal data value means among OBD device malfunction, communication status failure, vehicle defect, and driver's operation error,
The OBD device malfunction, communication state failure, vehicle defect, and driver's operation error are set as output values, and machine learning is performed by setting the vehicle model, year of manufacture, and abnormal data values as input values,
Thereafter, when a new abnormal data value is received, detecting which state the vehicle indicates among OBD device malfunction, communication state failure, vehicle defect, and driver's operation error, and guiding the vehicle to a user terminal. In the vehicle abnormal state detection system based on data collected through OBD (On Board Diagnostics) device,
It includes a server and a user terminal,
The user terminal is
Each vehicle registration information, data collected through the OBD device mounted on each vehicle, and vehicle data including GPS information of each user terminal are collected, and abnormal data values are removed from the vehicle data, and the normal data values are filter to remain,
The server is
Receive the normal data value and the abnormal data value from a plurality of user terminals, and based on the filtered normal data value, cargo transportation safety of the vehicle, vehicle history management information, depreciation cost of the vehicle, and abnormality by vehicle model It is determined whether the state has occurred and provided to the user terminal or other server, and using the abnormal data values, it is determined whether the OBD device malfunctions, communication status is bad, vehicle defect, and driving operation error occurs, the user terminal or to another server,
In the process of determining whether an abnormal state has occurred for each vehicle model, a plurality of state data of the vehicle to which the registered vehicle identification number and the manufacturer information of the OBD device being used by the user are mapped are collected from an external server, and the collected data is collected from each By storing each vehicle, categorizing data by condition information item to perform big data analysis, analyzing the correlation between normal data value and abnormal data value for each vehicle, and analyzing the correlation between condition information items, the vehicle model A system that detects the presence or absence of an abnormal state according to

Images