EP4047569A1 - Procédé, dispositif de traitement des données, appareil et système - Google Patents

Procédé, dispositif de traitement des données, appareil et système Download PDF

Info

Publication number
EP4047569A1
EP4047569A1 EP22157067.4A EP22157067A EP4047569A1 EP 4047569 A1 EP4047569 A1 EP 4047569A1 EP 22157067 A EP22157067 A EP 22157067A EP 4047569 A1 EP4047569 A1 EP 4047569A1
Authority
EP
European Patent Office
Prior art keywords
data
vehicle
route
machine learning
learning algorithm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP22157067.4A
Other languages
German (de)
English (en)
Inventor
Jürgen Vogt
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Vogt Juergen
Original Assignee
Vogt Juergen
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vogt Juergen filed Critical Vogt Juergen
Publication of EP4047569A1 publication Critical patent/EP4047569A1/fr
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G07C5/085—Registering performance data using electronic data carriers
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station

Definitions

  • the present invention relates in general and in particular to a method, a device for data processing and a system for detecting manipulation of trip data of a vehicle monitoring device and to a device for transmitting trip data from a vehicle monitoring device to detect manipulation of the trip data.
  • Monitoring devices for vehicles are generally known, in particular for commercial vehicles and trucks (trucks).
  • trucks Such control devices are also known as electronic tachographs.
  • electronic tachographs By law, such electronic tachographs must be provided in commercial goods transport to monitor driving and break times in trucks with a total weight of more than 7.5 t (tons).
  • the journey data recorded in this way can be read out via a communication interface on the electronic tachograph and, for example, transferred to a storage medium (e.g. USB stick).
  • identification cards In known electronic tachographs, identification cards (driver cards) are inserted, on which personalized card usage data are stored.
  • the data stored on the driver cards represent e.g. B. Information about the distance covered during the journey and information about the respective status of the driver. The status of the driver describes, for example, whether the driver is currently driving the truck, doing other work or taking a break.
  • the electronic tachograph is typically connected to a distance sensor ("KITAS" - Kienzle Sensor).
  • the distance sensor determines the revolutions of the drive axle via a Hall sensor, for example, and can also calculate the driving speed and the distance covered from the number of pulses (based on a unit of time).
  • a truck's communication bus e.g. CAN bus; CAN stands for "Controller Area Network”
  • the electronic tachograph receives additional movement information on the current driving speed of the vehicle from the engine control unit Truck. In a subsequent analysis, this movement information can be compared with the movement information determined by the distance sensor.
  • the journey data from the control device and the ticket inserted are typically stored with regard to the distance traveled, the driving speed over the last few days, any position data obtained via a connected GNS system (GNS stands for "Global Navigation System”), and the entered movement statuses (e.g. Steering, interruption, work and break) evaluated, which a driver z. B enters via a control panel of the control device.
  • GNS Global Navigation System
  • distance impulses the distance impulses from the distance sensor
  • distance signal distance signal
  • distance impulses be manipulated in order to manipulate journey data and thus make it more difficult to determine violations of the permissible maximum driving speed or of the driving and break time regulations.
  • the inserted tickets can be manipulated by making unauthorized copies.
  • the movement information coming from the engine control unit is also possibly manipulated; e.g. B. through changes to the engine control unit itself, in which emulators simulate a speed signal from the engine control unit.
  • the operating software of the control device is able to recognize such manipulations and to store corresponding error messages in the journey data, which are read out of the tachograph by the control bodies at a later point in time.
  • error messages are stored in the engine control unit, which can be read out later.
  • the situation is different if the distance signal has been successfully manipulated without the error detection routines in the control device having detected this manipulation.
  • the distance traveled/driving speed is then stored in such a way that the entries with manipulated movement states (driving and break times) may not be discovered during any checks.
  • the manipulations by changing the firmware in the control device are typically implemented in that the movement states (driving and break times) of the truck are no longer entered by the driver, but by the manipulated firmware of the control device, for example by storing the corresponding data in the control device .
  • the object of the present invention is therefore an improved method, an improved device for data processing and an improved system for determining manipulation of journey data of a control device in a vehicle, and a device for transmitting journey data from a control device in a vehicle to determine manipulation of the journey data in order, for example, to improve the detection of manipulations.
  • the present invention provides an apparatus for data processing, comprising an electronic circuit, the electronic circuit being set up to carry out the method according to the first aspect.
  • the method is applied in particular to trip data from a control unit of a truck or commercial vehicle, although the invention is not limited to these cases.
  • the vehicle type and/or the vehicle type is also determined or it is known, so that in general the determination of manipulation can also include the vehicle type or vehicle type, since, for example, the movement profile of a high-powered passenger car is different than that of a truck or a heavy-duty transporter .
  • the procedure can be carried out on site, e.g. B. in a control (e.g. by stopping) by control bodies, or in a later analysis of stored travel data.
  • the aim of the method is to determine whether manipulation of the trip data is likely or has taken place, although in some embodiments it is not important to determine the exact cause or the exact type of manipulation.
  • some embodiments provide for the inspection bodies to be shown a classification result which is indicative of e.g. B. an existing manipulation, a probable manipulation or no manipulation of the journey data, so that possible further steps could then be taken by the control bodies to determine the type and extent of the manipulation.
  • some embodiments relate to a device for data processing, wherein the device for data processing contains an electronic circuit that is set up to carry out the method described herein.
  • the electronic circuit of the device for data processing can have one or more processors (e.g. CPU, application processor, graphics processor, etc.), one or more memory elements (e.g. hard disk, RAM, ROM, semiconductor memory, etc.), one or more FPGAs ( "Field Programmable Gate Array"), one or more application specific circuits (ASICs - "Application Specific Integrated Circuit”) included and / or contain typical electronic components that are configured according to the execution of the method.
  • the method may be based on computer programs that include a sequence of instructions that, upon execution of the instructions, cause a computer/processor to perform the method described herein.
  • the method can be based partly on computer programs and partly on electronic circuits.
  • the electronic circuitry of the device for data processing contains a communication interface for data exchange with other computers, devices, etc. via a network, whereby the data communication can be wired or wireless.
  • the network can be a cellular network, a computer network (e.g. Internet), etc., and the electronic circuit of the device for data processing then contains appropriate hardware interfaces and implements appropriate communication protocols for data exchange.
  • trip data from the control device is obtained.
  • Travel data are e.g. B. such data that are stored on the recording device and the driver card (s), such. B. a driving speed profile (driving speed over time), mileage (distance covered) and the entered driving and break times.
  • This trip data therefore represents a movement profile of the vehicle within the recorded time period and therefore a movement profile of the vehicle on a route traveled by the vehicle.
  • the movement profile is characterized in particular by the driving speed profile and the driving and break times.
  • the device for data processing can load the trip data from a storage medium or receive it via a communication interface.
  • the movement profile of the vehicle can be compared with the movement profile of other vehicles that have traveled the same section.
  • a movement profile that is characteristic of the route section in particular a driving speed profile, can be determined on the basis of a large number of movement profiles of vehicles (a vehicle class such as trucks) on the route section.
  • a position of the vehicle is indicative of a route section if it is determined within the period of time of the recorded journey data. In some embodiments, a position of the vehicle is indicative of a route section if the The time of the position determination is shortly before or after the period of the recorded journey data. In some embodiments, from the presence of a position of the vehicle, part of the trip data can be associated with the position of the vehicle on the one hand and an area surrounding the position can be determined on the other hand, which is then indicative of a section of the route traveled by the vehicle (e.g. the indicate the position of a gas station on a motorway, so that a segment is a segment of the motorway).
  • the position can be determined from toll data or from position data from a possibly connected GNS system of the vehicle.
  • this data is not always available.
  • the device reads the trip data from the control device on site via a data bus and then transmits its own determined position and the trip data to the device for data processing. Since in some embodiments the position is also determined directly on site during the check, it is also indicative of a section of the route traveled by the vehicle, which then corresponds to a section of road in the vicinity of the checkpoint.
  • the electronic circuit of the device can consist of one or more processors (e.g. CPU, application processor, graphics processor, etc.), one or more memory elements (e.g. hard disk, RAM, ROM, semiconductor memory, etc.), one or more FPGAs ("Field Programmable Gate Array"), contain one or more application-specific circuits (ASICs - "Application Specific Integrated Circuit") and/or contain typical electronic components that configured appropriately to perform the procedure.
  • processors e.g. CPU, application processor, graphics processor, etc.
  • memory elements e.g. hard disk, RAM, ROM, semiconductor memory, etc.
  • FPGAs Field Programmable Gate Array
  • ASICs - "Application Specific Integrated Circuit” Application Specific Integrated Circuit
  • the electronic circuitry of the device contains a communication interface for exchanging data with other computers, devices, mobile communication devices, etc. over a network, where the data communication can be wired or wireless.
  • the network can be a cellular network, a computer network (e.g. Internet), etc. and the electronic circuitry of the device then contains appropriate hardware interfaces (e.g. LTE ("Long Term Evolution") module) and implements appropriate communication protocols for data exchange.
  • LTE Long Term Evolution
  • the electronic circuitry of the device can support Wi-Fi ® , Bluetooth ® , etc. for communication with mobile communication devices.
  • the electronic circuit of the device contains a GNS module for position determination, for example via GPS ("Global Positioning System”) or Galileo.
  • the electronic circuitry of the device contains interfaces/data buses for reading out the driving data and control unit data and then implements the corresponding communication protocols.
  • the travel data obtained and the at least one position of the vehicle obtained are input into a machine learning algorithm, the machine learning algorithm being set up (i.e. being trained) to determine whether, based on the movement profile of the vehicle and the at least one position of the vehicle obtained the travel data received has been manipulated.
  • the machine learning algorithm can be based on a neural network.
  • the machine learning algorithm can also be based on a SVM ("Support Vector Machine"), a logistic regression, a decision tree or the like.
  • the machine learning algorithm is set up to H. he is trained to determine a classification result for the journey data received, which indicates whether the journey data received has been manipulated.
  • a classification result is output for the driving data obtained, the classification result being indicative of a probability of whether the driving data has been manipulated.
  • control bodies it is intended to display the trip data and the classification result to the control bodies in some embodiments, so that possible further steps can then be carried out the control bodies could be initiated to determine the nature and extent of the manipulation.
  • the electronic circuit of the device is also set up to communicate with a mobile communication device and to transmit its own position and/or the journey data read out to the mobile communication device.
  • the electronic circuit of the device is further set up to receive a classification result for the transmitted journey data from the data processing device and to transmit the classification result to the mobile communication device.
  • the electronic circuit of the device is set up to enable the device to be controlled using the mobile communication device (e.g. notebook, smartphone, tablet, etc.) which, for example, is in the possession of the control bodies at the time of the control.
  • the mobile communication device e.g. notebook, smartphone, tablet, etc.
  • each of these possible route sections has a characteristic movement profile, in particular the driving speed profile for trucks, e.g. B. the driving speed profile in a city or on a country road is different than on a highway.
  • the machine learning algorithm is therefore trained, based on a large number of comparison data, to classify movement profiles of a vehicle on a route/a route section that has been driven into manipulated and non-manipulated movement profiles.
  • the comparison data can, for example, be recorded driving data from other real vehicles, which can then be classified accordingly and used for the training.
  • the comparison data can, for example, be trip data from training vehicles that have been driven on a large number of routes and were manipulated and/or not manipulated.
  • the comparison data can be based, for example, on traffic simulations or other known simulation methods.
  • environmental data of the route section are obtained and the environmental data obtained of the route section are incorporated into the machine learning algorithm entered, wherein the machine learning algorithm further determined based on the received environmental data of the route section, whether the received travel data are manipulated.
  • the environmental data can be determined based on the at least one position from digital maps and/or loaded from a memory.
  • the environmental data of the route section represent positions of parking lots, service areas, gas stations and/or toll stations.
  • the environmental data can be retrieved by wire and/or wirelessly.
  • the environmental data can also be received wirelessly via any radio devices that are arranged, for example, in parking lots, service areas, gas stations, toll booths and the like, but also via radio devices in other vehicles.
  • the environmental data can, for example, be retrieved (wirelessly) by the control bodies from other vehicles that are in the vicinity of the checkpoint or, for example, drive past the checkpoint.
  • position data and/or movement profiles of other vehicles can be used to determine a manipulation.
  • the movement profile of the vehicle contains break times, for example, the driving speed during the break time is practically zero and the break time can only have taken place at certain locations provided for this purpose, e.g. B. in parking lots, at service areas, at gas stations and/or at toll booths.
  • the distance to the position at which the break was taken can be determined therefrom. If the distance deviates from the actual distance to the parking lots, service areas, gas stations and/or toll booths on the route section, this could also be an indication of manipulation of the trip data.
  • Such pattern recognition can be trained on the machine learning algorithm in some embodiments.
  • route data of the route section can improve the accuracy of the classification result of the machine learning algorithm.
  • route data of the route section are obtained and the route data of the route section obtained are input into the machine learning algorithm, wherein the machine learning algorithm further determines whether the travel data received has been manipulated based on the route data of the route section obtained.
  • the route data of the route section represents a maximum speed profile, an elevation profile, past traffic jams and/or past traffic reports.
  • the road data can e.g. B. be determined based on the at least one position from digital maps and be determined by (official) traffic data platforms and / or loaded from a memory.
  • each route section is characterized by a predetermined maximum speed profile and a predetermined height profile, as a result of which characteristic patterns occur in the driving speed profile of a large number of vehicles in some embodiments.
  • a predetermined maximum speed profile Starting from a checkpoint, for example, if the permissible maximum speeds are observed, periods of time with the corresponding permissible maximum speeds result in some embodiments in the journey data or the driving speed profile, with the time interval between the periods of time also being characteristic.
  • characteristic patterns occur in some embodiments in the driving speed profile, e.g. B. a lower driving speed at high gradients, the time interval between the patterns being characteristic.
  • characteristic patterns occur when braking and accelerating, so that the machine learning algorithm can be trained to recognize the presence or absence of these patterns in the driving speed profile of the driving data obtained.
  • movement profiles in traffic jams or other traffic situations that can be determined on the basis of traffic reports (eg roadblocks, slippery roads, etc.).
  • vehicle ECU data can improve the accuracy of the classification result of the machine learning algorithm.
  • controller data which was at least partially recorded within the period of the trip data, of the vehicle is obtained and input into the machine learning algorithm, wherein the machine learning algorithm further determines whether the received trip data is manipulated based on the controller data received.
  • the control unit data can be obtained/read out from an engine control unit, an ABS (anti-lock braking system) control unit, an air bag control unit, a transmission control unit or the like.
  • ABS anti-lock braking system
  • the electronic circuit of the device is set up to read out the control unit data from the vehicle and to transmit it to the device for data processing via the network.
  • control unit data contain error data, with the error data representing error messages.
  • control devices store error messages and the error messages are stored in the form of so-called—and unchangeable—“frozen frames”.
  • error messages can contain, for example: the mileage, the time of the error, the driving speed, the engine speed, the oil pressure, the engine temperature, the pedal positions, etc. at the time of the error.
  • error messages are generated, for example, when the engine control light comes on, the ABS has triggered, the airbag has triggered, the lighting system is faulty, the oil pressure or the engine temperature are critical, etc.
  • pattern recognition can be further improved by comparing the error messages with the movement profile of the vehicle. For example, the occurrence of an error message due to the triggering of the ABS during a pause can be indicative of manipulated trip data.
  • control unit data are read out that have been logged over a period of time parallel to the trip data.
  • Telematics systems are known, in particular for trucks, which log the corresponding control unit data and, if necessary, transmit it to a server (for example the forwarding agent) in order to enable the technical condition of the vehicle fleet to be checked.
  • control unit data can represent engine speed, driving speed, oil pressure, engine temperature, pedal positions, fuel consumption, exhaust gas values, etc.
  • the machine learning algorithm is trained in some embodiments to classify the movement profiles as manipulated and not manipulated on the basis of the control unit data.
  • road data and the day of the week and time are obtained, the day of the week and the time being associated with the at least one position of the vehicle, the road data representing a road and a direction of travel on the route segment, the road data obtained and the day of the week and the time being be input into the machine learning algorithm and wherein the machine learning algorithm further determines whether the received trip data is manipulated based on the road data, the day of the week and the time.
  • the movement profile can be different in the morning than at noon, for example, due to different traffic situations, or it can be different during the week than at the weekend, so that this is also taken into account in the pattern recognition in some embodiments in order to further improve the pattern recognition.
  • the street and the direction of travel can be transmitted to the device, for example, when checking via the mobile communication device, which transmits the corresponding data to the device for data processing.
  • the device is therefore connected to the vehicle's control unit via a corresponding data bus during an on-site inspection in order to emulate vehicle journeys while stationary and to read out the travel data recorded by the control unit, which are then transmitted to the data processing device.
  • control bodies generate emulation data via a mobile communication device (for example via a computer program) and transmit this to the device.
  • the device then generates corresponding test signals which, for example, emulate distance signals from a distance sensor and pause times, which are then entered into the control device in order to emulate a trip with a predefined movement profile. From a comparison of the specified movement profile and the emulation movement profile, the classification of the machine learning algorithm can then be further improved, for example, in order to determine even minor deviations.
  • emulation travel data of the vehicle's control device and emulation data are obtained, the emulation travel data being based on test signals and the test signals being based on the emulation data, the emulation data emulating a movement profile of the vehicle and the emulation travel data obtained and the emulation data obtained input into the machine learning algorithm, wherein the machine learning algorithm further determines whether the received ride data is manipulated based on the received emulation ride data and the received emulation data.
  • test drive data could improve the accuracy of the machine learning algorithm's classification result.
  • the device is therefore used on a test drive with the vehicle.
  • the device is connected to the vehicle's control device via a corresponding data bus during the test drive (or after the test drive) in order to transmit the recorded test drive data and the positions determined during the test drive to the data processing device. From a comparison of the movement profile during the test drive and the positions, the classification of the machine learning algorithm could be further improved in order to identify even minor deviations.
  • test drive data from the vehicle's control device and test position data are obtained, the test position data being associated with the test drive data and representing positions during a test drive of the vehicle, the test drive data representing a movement profile of the vehicle during the test drive Represent a test drive and the test drive data obtained and the test position data obtained are entered into the machine learning algorithm and the machine learning algorithm further determines based on the test drive data received and the test position data received whether the drive data received are manipulated.
  • manipulated travel data could be determined independently of the type of manipulation, which can solve a major security problem in some embodiments.
  • the vehicle 2 is here a truck (hereinafter: truck) that was stopped at a checkpoint KP by the control bodies.
  • the truck 2 contains the control unit 3 and control units 4, the control units 4 here comprising an engine control unit and an ABS control unit and, for the sake of simplicity, are summarized below under “the control unit 4”.
  • the control bodies are in possession of a device 5 and a mobile communication device 6.
  • the device 5 contains data buses 5a and 5b for connecting to the control device 3 or to the control device 4.
  • Device 5 reads trip data 7 from control device 3 via data bus 5a and control device data from control device 4 via data bus 5b.
  • the device 5 contains a GPS module 5d and determines its own position 9, which is indicative of the position of the truck 2.
  • the device 5 transmits the journey data 7, the control device data 8 and the position of the device 9 to the mobile communication device 6 via a Bluetooth interface 5c.
  • the device 5 transmits the journey data 7, the control device data 8 and the position of the device 9 via a mobile radio interface 5e to a base station 10, which transmits them via a network 11 to a server 12 (device for data processing).
  • the server 12 contains a memory 13 on which a computer program is stored which implements a (trained) machine learning algorithm 14 and is executed by one or more processors (not shown).
  • the server 12 Based on the position 9 of the vehicle 2, the server 12 receives environmental data 15 and route data 16 from a database 17.
  • the travel data 7 obtained, the control unit data 8 obtained, the position 9 of the vehicle 2 , the environmental data 15 and the route data 16 are entered into the machine learning algorithm 14 .
  • the machine learning algorithm 14 determines a classification result 18 for the travel data 7 received, which is indicative of a probability as to whether the travel data 7 has been manipulated.
  • the classification result 18 is transmitted via the network to the device 5, which transmits the classification result 18 to the mobile communication device 6 of the control bodies.
  • control point KP is shown as an example and schematically, at which the vehicle 2 from 1 controlled by the control bodies.
  • the device 5 determines a position 9 during the check, which is indicative of the position of the vehicle 2 and thus also for the checkpoint KP.
  • Position 9 is therefore indicative of at least one section of the route traveled by vehicle 2.
  • Route A has a parking lot 20
  • route B has a rest area 21
  • route C has no rest area around checkpoint KP.
  • the device 5 reads the trip data 7 from the control device 3 of the vehicle 2 .
  • the solid line in Figure 2B shows the real motion profile 30 of vehicle 2 on route B.
  • the dotted line in Figure 2B shows the movement profile 31 of the vehicle 2 on the route B recorded with the control device 3, which can be extracted from the trip data 7 read out.
  • the real movement profile 30 has a consistently higher driving speed of the vehicle 2 than the recorded movement profile 31 .
  • the recorded movement profile 31 In contrast to the real movement profile 30, the recorded movement profile 31 also has a pause time between the times t1 and t2.
  • a first comparison movement profile 32 of route B (short-dashed line in Figure 2B ) was determined from a large number of comparative data from a large number of vehicles and from a large number of journeys with a training vehicle and represents a movement profile of the route B, which is calculated by the (trained) machine learning algorithm 14 1 classified as non-manipulated.
  • the first comparison movement profile 32 of the route B has a typical pause time between the times t3 and t4.
  • a second comparison movement profile 33 of route A was determined in the same way as route B and is based on the (trained) machine learning algorithm 14 1 classified as non-manipulated.
  • the second comparison movement profile 33 of the route A has a typical pause time between the times t5 and t6.
  • a third comparison movement profile 34 of route C (long dashed line) was determined analogously to route B and is from the (trained) machine learning algorithm 14 1 classified as non-manipulated.
  • the third comparison movement profile 34 of route C has no pause time.
  • the machine learning algorithm 14 determines that the recorded movement profile 31 for route C is to be classified as manipulated, for example due to the pause time between t1 and t2, the consistently significantly higher driving speed and the different course of the movement profiles 31 and 34 .
  • the route C also has a maximum speed profile and an altitude profile (route data 16 for route C), which means that the recorded movement profile 31 cannot have originated on route C.
  • the machine learning algorithm 14 determines that the recorded movement profile 31 for route A is to be classified as manipulated. For example, due to the pause time between t1 and t2 and not between t5 and t6 and the clearly different course of the movement profiles 31 and 33.
  • Route A also has a maximum speed profile and an altitude profile (route data 16 for route A), which means that the recorded movement profile 31 cannot have originated on route A.
  • the machine learning algorithm 14 determines that the recorded movement profile 31 for route B is to be classified as manipulated, for example due to the pause time between t1 and t2 and not between t3 and t4 and the temporally compressed course of the recorded movement profile 31 compared to the first comparison movement profile 32.
  • the machine learning algorithm 14 could still classify the recorded movement profile 31 as manipulated on route B due to the temporally compressed course of the recorded movement profile 31 compared to the first comparison movement profile 32 .
  • Figure 2C is shown schematically and by way of example how environmental data 15 improves the classification of the machine learning algorithm 14 .
  • the distance on the route B to the control point KP is plotted over time on the vertical axis (illustrated here as linearly increasing for the sake of illustration only).
  • the dotted line illustrates the distance to the control point KP based on the recorded movement profile 31.
  • the point 35 marks the distance at which the supposed break time was taken.
  • the short dashed line illustrates the distance to the control point KP based on the first comparison movement profile 32.
  • the point 36 marks the distance at which the typical pause time is taken.
  • Distance 37 marks the discrepancy between the two distances.
  • the environmental data show that there is only service area 21 on route B in the vicinity of checkpoint KP, where breaks can be taken.
  • the distance obtained from the environment data matches the distance at point 36.
  • the machine learning algorithm 14 therefore also classifies the recorded movement profile 31 as manipulated on route B based on the environmental data.
  • control unit data 8 could improve the classification of the machine learning algorithm 14 .
  • the read-out control unit data 8 have an error message 38 at time t7, which here, for example, reports the triggering of the ABS system.
  • this error message 38 occurs within the pause time between t1 and t2, so that the triggering of the ABS system at this point in time can be classified as very unlikely.
  • the machine learning algorithm 14 outputs a classification result 18 which is indicative of a manipulation of the journey data 7 .
  • FIG. 3 schematically illustrates in a block diagram an embodiment of a training method for a machine learning algorithm 14-t for determining a manipulation of trip data 7 of a control device 3 of a vehicle 2.
  • the machine learning algorithm 14-t is in the training phase here and is based on a neural network in this embodiment, although the invention is not limited to this case.
  • the machine learning algorithm 14 -t is trained with a training data set 40 .
  • the training data set 40 contains a large number of data sets, each data set of the large number of data sets comprising training drive data 7-t, training control device data 8-t, at least one position 9-t associated with the training drive data 7-t, training environment data 15 -t, training route data 16-t and a classification 41 ("label") which indicates whether the training trip data is manipulated or not.
  • the training data set 40 was determined using a large number of comparison data from a large number of vehicles and from a large number of journeys with a training vehicle, with manipulated and non-manipulated data being present.
  • the records (apart from the classification 41) are input into the machine learning algorithm 14-t, which based thereon outputs a classification result 18-t for each record.
  • the classification result 18-t and the classification 41 are entered into a loss function 42, the loss function 42 here being a cross entropy loss.
  • the weight changes 43 are output and the weights of the machine learning algorithm 14-t are updated accordingly.
  • the trained machine learning algorithm 14 with trained weights is available.
  • 4 13 schematically illustrates in a block diagram one embodiment of a general purpose computer 130.
  • General purpose computer 130 represents electronic circuitry with which data processing apparatus 12 and device 5 may be implemented as described herein.
  • the general purpose computer 130 has components 131 to 135, a GNS module 136 in the case of device 5, and a data bus 137.
  • Embodiments that use software, firmware, programs, or the like to perform the methods described herein may be installed on general purpose computer 130, which is then configured to suit the particular embodiment.
  • the general purpose computer 130 has a CPU 131 ("Central Processing Unit”) which can execute various types of procedures and methods as described herein, e.g. B. in accordance with programs stored in read-only memory (“ROM”) 132, stored in memory 134 and loaded into random access memory (“RAM”) 133.
  • ROM read-only memory
  • RAM random access memory
  • the CPU 131, ROM 132, RAM 133 and memory are connected to the data bus 137.
  • a communication interface 135 is connected to the data bus 137, which can be set up z. B. for communication via a local area network (LAN), a wireless local area network (WLAN), a mobile telecommunications system (GSM, UMTS, LTE, NR, etc.), Bluetooth, infrared, etc.
  • the communication interface implements appropriate hardware interfaces and communication protocols.
  • the GNS module 136 is connected to the data bus 137 and can determine a position in accordance with a global navigation system such as GPS or Galileo.
  • FIG. 12 schematically illustrates in a flow chart an embodiment of a method 200 for determining a manipulation of trip data of a control device of a vehicle, which in some embodiments runs on the general-purpose computer 130 .
  • trip data is obtained, where the trip data represents a motion profile of the vehicle over a driven route, as discussed herein.
  • At 202 at least one position of the vehicle is obtained, the at least one position of the vehicle being indicative of at least a portion of the route traveled, as discussed herein.
  • route data of the route segment is obtained as discussed herein.
  • link controller data is obtained, as discussed herein.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
EP22157067.4A 2021-02-17 2022-02-16 Procédé, dispositif de traitement des données, appareil et système Pending EP4047569A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102021103697.6A DE102021103697A1 (de) 2021-02-17 2021-02-17 Verfahren, vorrichtung zur datenverarbeitung, gerät und system

Publications (1)

Publication Number Publication Date
EP4047569A1 true EP4047569A1 (fr) 2022-08-24

Family

ID=80449090

Family Applications (1)

Application Number Title Priority Date Filing Date
EP22157067.4A Pending EP4047569A1 (fr) 2021-02-17 2022-02-16 Procédé, dispositif de traitement des données, appareil et système

Country Status (2)

Country Link
EP (1) EP4047569A1 (fr)
DE (1) DE102021103697A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180315260A1 (en) * 2017-05-01 2018-11-01 PiMios, LLC Automotive diagnostics using supervised learning models
DE102017209817A1 (de) * 2017-06-09 2018-12-13 Robert Bosch Gmbh Verfahren zur Manipulationssicherung eines Kilometerstandes eines Fahrzeugs
DE102018201064A1 (de) * 2018-01-24 2019-07-25 Bayerische Motoren Werke Aktiengesellschaft Verfahren zum überwachen einer zurückgelegten gesamtwegstrecke sowie vorrichtung, fahrzeug und server
US20190318267A1 (en) * 2018-04-12 2019-10-17 Baidu Usa Llc System and method for training a machine learning model deployed on a simulation platform
DE102019119784A1 (de) * 2019-07-22 2021-01-28 Bayerische Motoren Werke Aktiengesellschaft Verfahren und System zum Erkennen einer Manipulation eines Fahrzeugs

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102012215601A1 (de) 2012-09-03 2014-03-06 Continental Automotive Gmbh Verfahren und Vorrichtung zum Ermitteln eines Werts einer bewegungsabhängigen Größe
DE102019135608A1 (de) 2019-12-20 2021-06-24 Bayerische Motoren Werke Aktiengesellschaft Verfahren, Vorrichtung und System zur Detektion von anomalen Betriebszuständen eines Geräts

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180315260A1 (en) * 2017-05-01 2018-11-01 PiMios, LLC Automotive diagnostics using supervised learning models
DE102017209817A1 (de) * 2017-06-09 2018-12-13 Robert Bosch Gmbh Verfahren zur Manipulationssicherung eines Kilometerstandes eines Fahrzeugs
DE102018201064A1 (de) * 2018-01-24 2019-07-25 Bayerische Motoren Werke Aktiengesellschaft Verfahren zum überwachen einer zurückgelegten gesamtwegstrecke sowie vorrichtung, fahrzeug und server
US20190318267A1 (en) * 2018-04-12 2019-10-17 Baidu Usa Llc System and method for training a machine learning model deployed on a simulation platform
DE102019119784A1 (de) * 2019-07-22 2021-01-28 Bayerische Motoren Werke Aktiengesellschaft Verfahren und System zum Erkennen einer Manipulation eines Fahrzeugs

Also Published As

Publication number Publication date
DE102021103697A1 (de) 2022-08-18

Similar Documents

Publication Publication Date Title
EP0700009B1 (fr) Procédé et système d'évaluation individuelle du risque véhicule automobile
DE202019005891U1 (de) Fahrzeugtelematik von Fahrzeugunfällen
DE102012021919B4 (de) Modell-basiertes Effizienz-Scoring in der Automobiltechnik
DE102008012660A1 (de) Serverbasierte Warnung vor Gefahren
DE102012219631A1 (de) Verfahren und Vorrichtung zum Detektieren von zumindest einer Fahrbahnunebenheit
WO2009027122A1 (fr) Unité de mise à jour et procédé de mise à jour d'une carte numérique
CN206684779U (zh) 一种基于adas智能车载终端的车险管理服务系统
DE102015213538A1 (de) Verfahren und System zum Warnen vor einer Falschfahrt eines Fahrzeugs
DE112018005030T5 (de) Verwaltungseinrichtung, fahrzeug, überprüfungseinrichtung undfahrzeugüberprüfungssystem sowie informationsverarbeitungsverfahren dafür
DE102018126830A1 (de) Vorrichtung und Steuereinheit zur Automatisierung einer Zustandsänderung einer Fensterscheibe eines Fahrzeugs
EP3446302B1 (fr) Procédé, dispositif et agencement de poursuite d'objets en mouvement
DE102016219124A1 (de) Verfahren und Vorrichtung zum Erstellen einer dynamischen Gefährdungskarte
DE102020206128A1 (de) Verfahren zum Steuern einer flottenbasierten Zustandsüberwachung eines Straßenabschnitts eines Straßennetzes sowie zugehöriges System und Kraftfahrzeug und zugehörige Servereinrichtung
DE102012222931A1 (de) Verfahren und Vorrichtung zur Ermittlung einer Position und/oder Art einer Straßeninfrastruktureinrichtung
DE102017002305A1 (de) Feststellen eines Fahrzeugnutzungsmodus
DE102019117136A1 (de) Kommunikation und steuerung für verkehrsinfrastruktur
EP2176836A1 (fr) Procédé de contrôle d'un message de position du véhicule émis par un véhicule et un émetteur-récepteur destiné à être utilisé dans un véhicule
EP4047569A1 (fr) Procédé, dispositif de traitement des données, appareil et système
EP2913792A1 (fr) Procédé de détection d'une caractéristique de mouvement d'un véhicule
DE102022202165A1 (de) Verfahren zum Bereitstellen einer Fahrstreifenlokalisierung für ein Kraftfahrzeug in einem Gebiet einer Infrastruktureinrichtung
WO2022028811A1 (fr) Système et procédé de mise en correspondance par cartes de positions de gnss d'un véhicule
DE102015015868A1 (de) Erkennen von Verkehrsregelungseinrichtungen
AT524959B1 (de) Datenerfassung im Fahrzeug
DE102013003035A1 (de) Fahrroutenerkennung von Kraftfahrzeugen
EP2772886B2 (fr) Système de tableau de bord électronique de véhicule et procédé de contrôle correspondant

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20230222

RBV Designated contracting states (corrected)

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR