Method, device, computer program and computer-readable storage medium for determining at least one fault vehicle

Abstract

The invention relates to a method, a device, a computer program and a computer-readable storage medium for determining a faulty vehicle, the faulty vehicle being a subset of a predetermined main set of vehicles (2) and the vehicles (2) being divided into a plurality of vehicle types, the method comprising:-determining respective data channel actual values, each data channel actual value represents a number of data transmitted in a first data channel or a second data channel for the at least one vehicle (2), determining a vehicle-specific ratio on the basis of a ratio of a respective data channel actual value of a first data channel to a data channel actual value of a second data channel for the at least one vehicle (2), determining a deviation value for the vehicle, each deviation value represents a deviation of a specific value from a predetermined expected value of the vehicle type,-classifying as a function of the deviation values whether the at least one vehicle is faulty.

Description

Technical Field

[0001] A method for determining at least one faulty vehicle is specified. Furthermore, a device, a computer program and a computer-readable storage medium are specified. Summary of the invention

[0002] The object to be achieved is to specify a method in which at least one faulty vehicle can be determined particularly simply and quickly. In addition, a device and a computer program are to be specified, which are capable of executing such a method. In addition, a computer-readable storage medium having such a computer program is to be specified.

[0003] The object is achieved by the method and the technical solution of the independent claims. Advantageous embodiments, implementations and further developments are the technical solution of the respective dependent claims.

[0004] According to a first aspect, the present invention relates to a method for determining at least one vehicle having a fault. The at least one vehicle having a fault is a subset of vehicles of a predetermined main set.

[0005] The vehicles of the predetermined main set are networked with each other, for example. The vehicles of the predetermined main set are networked with each other, for example, by means of a device. For example, each vehicle in the predetermined main set of vehicles is connected to a device, in particular an external device, by means of a communication connection. The device is, for example, a server, in particular a backend server.

[0006] The vehicles of the predetermined main set are divided into a plurality of vehicle types. The vehicle types, for example, relate to type identifications of vehicles. For example, each vehicle type includes a plurality of vehicles in the vehicle. Vehicles included in one vehicle type, for example, are not included in other vehicle types. The vehicle types, for example, group vehicles.

[0007] According to at least one embodiment of the method, corresponding data channel actual values ​​are determined which respectively represent the amount of transmit data for at least one vehicle in the first data channel or in the second data channel.

[0008] For example, the data channel actual value is determined as a function of a time interval. The time interval is, for example, at least 1 hour and at most 48 hours, in particular 24 hours. In particular, the time interval represents a day of the week.

[0009] For example, the transmission data is transmitted by at least one vehicle during vehicle operation to an external device, which stores and processes the transmission data. For example, the transmission data of the at least one vehicle within the time interval are processed in order to determine the corresponding data channel actual value. The data channel actual value relates to the amount of transmission data within the time interval, for example.

[0010] The transmitted data are, for example, messages containing status data of the at least one corresponding vehicle. If the vehicle is in operation, the vehicle transmits, for example, a predetermined message containing status data to an external device. For example, the status data are vehicle data that are displayed to a user in the vehicle and / or on a mobile device.

[0011] A data channel may represent a channel divided into a plurality of frames, which in turn may be divided into a plurality of time slots. Similarly, a data channel may represent a channel divided into a plurality of time blocks or frequency blocks. Furthermore, a data channel may represent a resource that is utilized by a predetermined unit, such as a sensor or a controller.

[0012] According to at least one embodiment of the method, a vehicle-specific ratio is determined based on a ratio of a corresponding data channel actual value of a first data channel to a data channel actual value of a second data channel for the at least one vehicle. For example, in the vehicle-specific ratio, the amount of transmit data of the first data channel (represented by the data channel actual value of the first data channel) is compared with the amount of transmit data of the second data channel (represented by the data channel actual value of the second data channel).

[0013] According to at least one embodiment of the method, an expected value is predetermined. The predetermined expected value is determined, for example, in a vehicle type-specific manner. The expected value is based on a ratio of all vehicles of a main set of the corresponding vehicle type.

[0014] The expected value can represent, for example, an average value of the ratio of all vehicles of a vehicle type. For example, the expected value of a vehicle type is determined as a function of a time interval. The time interval is, for example, at least 1 hour and up to 48 hours, in particular 24 hours. In particular, the time interval for determining the expected value is related to the time interval for determining the actual value of the data channel. For example, the expected value of the vehicle type is determined in time after the ratio of at least one vehicle is determined. In an advantageous manner, the expected value is therefore not static but can be changed dynamically.

[0015] According to at least one embodiment of the method, a deviation value is determined for at least one vehicle, wherein the deviation value represents a deviation of the ratio from an expected value. The deviation value may, for example, represent a difference between the ratio of the at least one vehicle and an expected value for a vehicle type of the at least one vehicle. For example, each vehicle of the predetermined main set has a deviation value.

[0016] In addition, each vehicle of the main set has, for example, at least one characteristic in addition to the deviation value. The characteristic includes, for example, one of the following information: vehicle type, product update, software version, combination of controllers, configured local market, backend center, production date. The vehicles of the main set include, for example, at least partially the same characteristics.

[0017] For example, information including product updates is given, which includes the type of update of the software, in particular the control software, of the vehicle. Similarly, information including the software version is given: in what condition the software, in particular the control software, of the vehicle is. Information including the combination of controllers is given, for example: which controllers are built into the vehicle and / or which controllers communicate with each other. Information including the configured home market is given: in which geographical area the vehicle is mainly operated. Information including the backend center is given: with which external backend center the vehicle is connected.

[0018] According to at least one embodiment of the method, a classification is performed based on the deviation value as to whether the at least one vehicle is defective or not. If the deviation value is greater than a predetermined expected value, the at least one vehicle is classified as defective, for example.

[0019] By dividing into two data channels, the faulty vehicle can be precisely determined by determining a vehicle-specific ratio value via the corresponding data channel actual value of the first data channel or the second data channel. By determining the deviation of the ratio value from the expected value, the deviation value is determined independently of the driving behavior of the corresponding vehicle. In this way, the deviation value can be correctly determined for vehicles that have not / hardly transmitted data within a certain period of time, for example due to long parking times when the vehicle is not used. In this way, it is more efficient and less prone to errors to classify whether a vehicle is faulty or not based on the deviation value.

[0020] According to at least one embodiment of the method, the at least one vehicle is assigned to a subgroup according to the deviation value. The vehicle classified as faulty is assigned to a predetermined subgroup according to at least one predetermined characteristic. Whether the at least one vehicle is faulty is determined by comparing the deviation value with an expected value. For example, the at least one vehicle is classified as faulty when the deviation value exceeds the expected value by 1%, 5%, or 10%.

[0021] For example, the subgroup includes faulty vehicles in which the deviation value is relatively large. The vehicle-specific ratio value of the vehicles in the subgroup of faulty vehicles therefore differs from the vehicle-type-specific expected value of the vehicles in the subgroup of faulty vehicles. That is, the vehicles in the subgroup of faulty vehicles send significantly less or significantly more data on the first data channel than on the second data channel compared to the expected value.

[0022] For example, such a method makes it possible to determine particularly easily and quickly a subgroup comprising faulty vehicles which, for example, have common properties which are responsible for the fault.

[0023] If the fault, for example, only involves a subset of vehicles of a predefined main set, in particular a subset of networked vehicles of a fleet, a subgroup of faulty vehicles can be identified by the given method. The subgroup includes, for example, faulty vehicles that have only certain vehicle types with a certain software version and / or a certain production date at one backend center.

[0024] This allows the properties of the defective vehicle to be known and remedial measures to be initiated in a targeted manner.

[0025] According to at least one embodiment of the method, when determining the subgroup of faulty vehicles, a global median is determined, which represents all deviation values ​​of the vehicles of the predetermined main set. In particular, the global median is the median of all deviation values.

[0026] According to at least one embodiment of the method, when determining the subgroup of faulty vehicles, at least one first subgroup is determined as a function of a first characteristic, such as the vehicle type of the vehicle.

[0027] According to at least one embodiment of the method, the at least one first subgroup has a first median which has a maximum difference with respect to a global median.

[0028] According to at least one embodiment of the method, when determining the subgroup of faulty vehicles, at least one second subgroup and at least one third subgroup are generated from the at least one first subgroup.

[0029] According to at least one embodiment of the method, the at least one second subgroup has a second median value as a function of a second characteristic. The second characteristic is, for example, a product update of the vehicle. The second characteristic is in particular different from the first characteristic.

[0030] According to at least one embodiment of the method, the at least one third subgroup has a third median value according to a third characteristic. The third characteristic is, for example, a software version of the vehicle. The third characteristic is in particular different from the first characteristic. Likewise, the third characteristic is in particular different from the second characteristic.

[0031] According to at least one embodiment of the method, the difference between the second median and the third median is maximized.

[0032] By determining a global median representing all deviation values ​​of the vehicles of a predetermined main set and a median for each additional subgroup, which represents all deviation values ​​of the vehicles within the corresponding subgroup, it is ensured that faulty vehicles in the main set can be distinguished from non-faulty vehicles.

[0033] For example, further subgroups according to further characteristics are generated from the at least one second subgroup and / or the at least one third subgroup.

[0034] According to at least one embodiment of the method, the subgroup of faulty vehicles is determined as a function of predetermined group variables of the second subgroup and of the third subgroup.

[0035] For example, the predetermined population variable is an abort criterion for the method. In this case, the subgroup of faulty vehicles is formed by a subgroup that is smaller than the predetermined population variable. The predetermined population variable of the subgroup of faulty vehicles is predetermined based on a statistical correlation. The predetermined population variable is, for example, so large that no overfitting occurs. For example, the predetermined population variable of the subgroup of faulty vehicles includes at least 500 vehicles and at most 5,000 vehicles.

[0036] If the population parameter of the first subgroup and / or the second group is greater than a predetermined population parameter, further subgroups are generated from the second subgroup and / or the third subgroup. If the population parameter of at least one of the further subgroups is less than a predetermined population parameter, the method ends, for example.

[0037] According to at least one embodiment of the method, the first characteristic, the second characteristic and the third characteristic each include at least one of the following information: vehicle type, product update, software version, combination of controllers, configured local market, backend center, production date. If further subgroups are generated, the further characteristics also include one of the aforementioned information.

[0038] According to at least one embodiment of the method, the first characteristic, the second characteristic and the third characteristic are different from one another. In particular, when generating further subgroups, these further characteristics are also different from one another.

[0039] According to a second aspect, the present invention relates to a device for determining a faulty vehicle. The device is configured to carry out the method described herein. All features of the embodiment disclosed in connection with the method are therefore also disclosed in connection with the device, and vice versa.

[0040] According to a third aspect, the present invention relates to a computer program, wherein when the instructions are executed by a computer, the computer program causes the computer to perform the method described herein.

[0041] According to a fourth aspect, the present invention relates to a computer-readable storage medium on which the computer program described herein is stored. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Exemplary embodiments of the invention are explained in more detail below with reference to schematic drawings.

[0043] In the figure:

[0044] Figure 1 A flow chart showing a method according to one embodiment is shown,

[0045] Figure 2 A schematic diagram showing a system having a device according to an embodiment, and

[0046] Figure 3 A schematic diagram is shown for determining a faulty subgroup in a method according to one exemplary embodiment. DETAILED DESCRIPTION

[0047] In accordance with Figure 1 In the flowchart of the method of the embodiment of the invention, method step S1 is first performed, in which a data channel actual value is determined for each vehicle of a predetermined main set from the amount of transmitted data in the first data channel or the second data channel within a day of the week.

[0048] For example, each vehicle 2 of a predetermined master set of a networked fleet is designed to send data during operation to a device 1, in particular an external device, via a first data channel and at least one second data channel. These data are predetermined messages and, for example, each include status data of the corresponding vehicle 2.

[0049] In a subsequent method step S2 , a vehicle-specific ratio can be determined for each vehicle 2 of the predetermined main set, which specifies the ratio of the amount of transmitted data in the first data channel to the amount of transmitted data in the second data channel on a day of the week.

[0050] The determination of the ratio can take place temporally after the determination of the actual value of the data channel.

[0051] In a further method step S3 , an expected value can be formed for each vehicle type from the ratio of each vehicle 2 of the predetermined main set, which represents the average value over all ratios of the vehicles of the predetermined main set of the respective vehicle type.

[0052] The expected value may be generated after the ratio is determined.

[0053] Next, in method step S4, a deviation value can be determined for each vehicle of the predetermined main set. The deviation value can be determined by means of a difference between the ratio value and an expected value.

[0054] In a further method step S5, the deviation value can be used to classify whether a vehicle of the predefined main set is defective. Whether a vehicle is defective can be determined by comparing the deviation value of the respective vehicle with an expected value for the respective vehicle type. If the deviation value exceeds or falls below the expected value by 5 percent, the vehicle is classified as defective, for example.

[0055] Next, in method step S6, a subgroup of faulty vehicles is determined based on the deviation value, wherein the ratio of the subgroup of faulty vehicles is less than an expected value. The faulty vehicles each include at least one characteristic, wherein the characteristics are the same. If the ratio of the vehicles within a day of the week is significantly less than the expected value within a day of the week, in particular within the same day of the week, the probability of a fault being caused by the characteristic increases.

[0056] according to Figure 2 The system of the exemplary embodiment of comprises a device 1, in particular an external device, which is designed to be connected to a vehicle 2 via a communication connection 3. The communication connection 3 is designed to transmit a sent, predetermined message to the device 1.

[0057] The device 1 is configured to perform Figure 1 method.

[0058] The device is configured, for example, in a backend server.

[0059] For this purpose, the device 1 has in particular a computing unit, a program and data memory and, for example, one or more communication interfaces. The program and data memory and / or the computing unit and / or the communication interface can be embodied in one structural unit and / or distributed over a plurality of structural units.

[0060] In particular, a program for determining a faulty vehicle is stored on the program and data memory of the device 1 for carrying out the method, which program processes the method described above.

[0061] according to Figure 3 First, a first subgroup SG1 is determined according to a first characteristic. The first characteristic, for example, relates to information on a first product update. All vehicles of a predetermined main set having the characteristic are included in the first subgroup SG1.

[0062] In particular, the first subgroup SG1 has a first median having the largest difference with respect to a global median, wherein the global median represents all deviation values ​​of the vehicle 2. For example, the first subgroup SG1 includes 600,000 vehicles.

[0063] Next, the second subgroup SG2 and the third subgroup SG3 are generated from the first subgroup SG1. The second subgroup SG2 includes, for example, vehicles of the first subgroup SG1 in which the ratio is equal to the expected value. The third subgroup SG3 includes, for example, vehicles of the first subgroup SG1 in which the ratio is different from the expected value.

[0064] The second subgroup SG2 includes vehicles according to a second characteristic. The second characteristic, for example, relates to information on a second product update. All vehicles of the second subgroup SG2 thus include vehicles having the first characteristic and the second characteristic. In addition, the second subgroup SG2 has a second median.

[0065] The third subgroup SG3 includes vehicles according to a third characteristic. The third characteristic, for example, relates to information on the local market. All vehicles of the third subgroup SG3 therefore include vehicles having the first characteristic and the third characteristic. In addition, the third subgroup SG3 has a third median.

[0066] In this case, the second subgroup SG2 and the third subgroup SG3 are selected such that the difference between the second median and the third median is maximized.

[0067] Next, further subgroups according to further characteristics, namely, a fourth subgroup SG4 and a fifth subgroup SG5, are generated from the third subgroup SG3. The fourth subgroup SG4, for example, includes the vehicles of the third subgroup SG3 in which the ratio is equal to the expected value. The fifth subgroup SG5, for example, includes the vehicles of the first subgroup SG1 in which the ratio is different from the expected value. For example, the fifth subgroup SG5 also includes only 15,000 vehicles.

[0068] The fifth subgroup SG5 is in accordance with Figure 1 The method associated with an embodiment corresponds to a subgroup of faulty vehicles. Reference numerals list

[0069] 1 device

[0070] 2 Vehicles

[0071] 3 communication device

[0072] SG1 First Subgroup

[0073] SG2 Second subgroup

[0074] SG3 Third Subgroup

[0075] SG4 Fourth Subgroup

[0076] SG5 Fifth Subgroup

[0077] S1..S6 Method Steps

Claims

1. A method for determining at least one vehicle having a fault, wherein: The at least one vehicle having a fault is a subset of vehicles (2) of a predetermined main set, and the vehicles (2) are divided into a plurality of vehicle types, the method comprising: - determining a corresponding data channel actual value, which in each case represents the amount of transmitted data in the first data channel or in the second data channel for the at least one vehicle (2), - determining a vehicle-specific ratio value based on a ratio of a corresponding data channel actual value of a first data channel to a data channel actual value of a second data channel for the at least one vehicle (2), - determining deviation values ​​for said at least one vehicle, wherein each deviation value represents a deviation of said ratio from a predetermined expected value for said vehicle type, - Classifying, based on the deviation value, whether the at least one vehicle is defective or not.

2. The method according to claim 1, wherein: The expected value is determined in a vehicle-type-specific manner based on a ratio of all vehicles (2) of a main set of the respective vehicle type.

3. The method according to claim 1, wherein: Vehicles classified as faulty are assigned to predetermined subgroups according to at least one predetermined characteristic.

4. The method according to claim 3, wherein: Determine a subgroup of faulty vehicles, where - determining a global median representing all deviation values ​​of the vehicles of a predetermined master set, - at least one first subgroup (SG1) is determined according to a first characteristic, wherein: - the at least one first subgroup (SG1) has a first median having a maximum difference with respect to a global median, - generating at least one second subgroup (SG2) and at least one third subgroup (SG3) from the at least one first subgroup (SG1), wherein: the at least one second subgroup (SG2) having a second median according to a second characteristic, - the at least one third subgroup (SG3) has a third median according to a third characteristic, and --Maximize the difference between the second median and the third median.

5. The method according to claim 4, wherein: The subgroup of faulty vehicles is determined based on predetermined group parameters of the second subgroup and the third subgroup.

6. The method according to claim 4 or 5, wherein: - the first characteristic, the second characteristic and the third characteristic respectively have at least one of the following information: vehicle type, product update, software version, combination of controllers, configured local market, backend center, production date, and - The first characteristic, the second characteristic and the third characteristic are different from each other.

7. The method according to claim 1, wherein: Each data channel actual value is determined according to a plurality of time intervals, and the time intervals respectively represent days of a week. 8 . A device for determining at least one faulty vehicle, the device being designed to carry out a method according to claim 1 . 9 . A computer program comprising instructions which, when the computer program is executed by a computer, cause the computer to carry out the method according to claim 1 . 10 . A computer-readable storage medium on which the computer program according to claim 9 is stored.

Images