Method and device for processing data from vehicles connected to a wireless communication network

Abstract

The present invention relates to a method and device for processing data from vehicles connected to a wireless communication network. To this end, a group (11) of connected vehicles is selected from a set of vehicles based on first criteria, and then a set of samples (111, 112) of connected vehicles are selected from the group (11) based on second criteria. Usage data from each connected vehicle in the group (11) are collected to determine statistical criteria for the group (11) and for each sample (111, 112). These statistical criteria are compared to select the most representative sample of the group (11) of connected vehicles. Figure for the abstract: Figure 1

Description

Title of the invention: Method and device for processing data from vehicles connected to a wireless communication network Technical field

[0001] The invention relates to methods and devices for processing vehicle data, in particular automobiles, connected to a wireless communication network. The invention relates to methods and devices for communicating vehicle data in a wireless communication network. The invention relates in particular to a method and a device for calculating a mission profile from data obtained from a sample of connected vehicles. The invention relates in particular to a method and a device for learning a life cycle prediction model of a member or component of a vehicle from learning data obtained from a sample of connected vehicles. Technological background

[0002] Contemporary vehicles are made up of a large number of components or organs that are susceptible to failure. To reduce the number of failures and correctly size these components and organs, it is important for vehicle manufacturers and their subcontractors to know precisely the constraints and stresses undergone by these components and organs during use of the vehicle.

[0003] To do this, it is known to obtain data relating to the use of vehicles according to mission profiles determined from the manufacturer's customers, for example by sending these customers one or more questionnaires relating to the use of the vehicles by the customers. It is also known to obtain such data by carrying out driving under conditions determined according to the mission profiles, in particular on circuits.

[0004] Collecting data using known methods poses several problems. The cost associated with collecting this data is high, the volume of data obtained is limited and the representativeness of the vehicles is also limited due to the generally small number of vehicles considered. Furthermore, since data collection campaigns are complex to implement and costly, changes in the use of vehicles by customers are generally not known and therefore not taken into account when it comes to developing components or organs.

[0005] Having a better understanding of vehicle use in real-life conditions is an important issue for car manufacturers, for example to improve mission profile calculations to better size components based on their actual use by customers or to learn prediction models of breakdowns based on training data reflecting actual vehicle usage. Summary of the present invention

[0006] An object of the present invention is to solve at least one of the problems of the technological background described above.

[0007] Another object of the present invention is, for example, to improve the collection of vehicle usage data.

[0008] According to a first aspect, the present invention relates to a method for processing data from vehicles connected to a wireless communication network, said method comprising the following steps: a) selecting, from a set of vehicles, a group of vehicles connected to the wireless network via a wireless connection based on a set of first selection criteria, at least one first selection criterion of the set corresponding to an intrinsic vehicle characteristic; b) selecting, from the group of connected vehicles, a set of samples of connected vehicles based on a set of second selection criteria; (c) receiving, from each connected vehicle of the group via the wireless connection, data representative of the use of each connected vehicle over a determined period of time; d) determining, for each connected vehicle of the group, a set of parameters from the data representative of the use of each connected vehicle, a plurality of values ​​being determined at different time instants of the time period determined for each parameter of the set of parameters; e) for each parameter of the set of parameters, determining at least one first statistical value for the group of connected vehicles by statistical processing of the pluralities of values ​​determined for each connected vehicle of the group of connected vehicles; (f) for each parameter of the parameter set, determining at least one second statistical value for each sample of the sample set by statistical processing of the pluralities of values ​​determined for each connected vehicle of each sample; (g) for each sample, determining an error by comparing the second statistical values ​​with the first statistical values; and h) selecting a sample from the set of samples based on the error associated with each sample.

[0009] The selection from a group of connected vehicles of a sample of this group (i.e. a subgroup) in a set of samples according to an error obtained by comparison of representative values ​​of each sample with representative values ​​of the vehicle group calculated according to the same criteria makes it possible to obtain the most representative sample of the group of connected vehicles. The collection of usage data from the connected vehicles forming this sample makes it possible to obtain data representative of the usage of the group of vehicles in real conditions, the data being obtained directly from the vehicles in the sample via the wireless connection linking these connected vehicles to a wireless network, for example a terrestrial cellular network.

[0010] The collection of data representative of the actual use of the vehicles is facilitated in that this data can be obtained at any time, via the wireless connection, from a reduced set of vehicles connected to the wireless network and representative of a larger group of connected vehicles.

[0011] The data thus obtained are for example used to establish various mission profile calculations necessary for the dimensioning of components or organs embedded in vehicles of the same type as the vehicles forming the group of connected vehicles for example.

[0012] According to a variant, the error, noted Err, is determined via the following function: Err — W *(Cr- C )2 with 'c parameter name^rc in the parameter set, Wi a weighting factor associated with the index parameter i, Cr; the first statistical value associated with the index parameter i, and Ci the second statistical value associated with the index parameter i.

[0013] According to another variant, the selected sample corresponds to the sample having the lowest associated error.

[0014] According to yet another variant, the selection of a sample further comprises a comparison of the error associated with the selected sample to a determined threshold value, the sample having the lowest associated error being selected only when the lowest associated error is less than the determined threshold value.

[0015] According to an additional variant, when the lowest associated error is greater than the determined threshold value, the method further comprises the following steps: - selecting a new set of samples from said group of connected vehicles based on a set of third selection criteria; and - repeating steps f) to h) by replacing the set of samples with the new set of samples.

[0016] According to another variant, the set of second selection criteria comprises: - a number of samples forming the set of samples; and / or - a number of connected vehicles included in each sample of the set of samples; and / or - a type of selection of connected vehicles forming each sample from a random selection and a deterministic selection.

[0017] According to another variant, the method further comprises a step of learning a life cycle prediction model of at least one vehicle component from learning data received from each connected vehicle of the selected sample via the wireless connection, the learning data comprising the representative usage data of each connected vehicle of the selected sample.

[0018] According to a second aspect, the present invention relates to a device for processing data from vehicles connected to a wireless communication network, the device comprising a memory associated with a processor configured for implementing the steps of the method according to the first aspect of the present invention.

[0019] According to a third aspect, the present invention relates to a system comprising a device as described above according to the second aspect of the present invention and a group of vehicles connected to the device via a wireless connection.

[0020] According to a fourth aspect, the present invention relates to a computer program which comprises instructions adapted for executing the steps of the method according to the first aspect of the present invention, in particular when the computer program is executed by at least one processor.

[0021] Such a computer program may use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0022] According to a fifth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to the first aspect of the present invention.

[0023] On the one hand, the recording medium may be any entity or device capable of storing the program. For example, the medium may comprise a storage means, such as a ROM memory, a CD-ROM or a microelectronic circuit type ROM memory, or a magnetic recording means or a hard disk.

[0024] Furthermore, this recording medium may also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or hertzian radio or by self-directed laser beam or by other means. The computer program according to the present invention may in particular be downloaded from an Internet-type network.

[0025] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to perform or to be used in performing the method in question. Brief description of the figures

[0026] Other characteristics and advantages of the present invention will emerge from the description of the particular and non-limiting exemplary embodiments of the present invention below, with reference to the appended figures 1 to 4, in which:

[0027] [Fig.l] schematically illustrates a communication environment for connected vehicles, according to a particular exemplary embodiment of the present invention;

[0028] [Fig.2] schematically illustrates a process for processing data obtained from at least part of the connected vehicles of [Fig.l], according to a first particular and non-limiting example of the present invention;

[0029] [Fig.3] illustrates a device configured for processing at least a portion of the connected vehicles of [Fig.l], according to a particular and non-limiting exemplary embodiment of the present invention.

[0030] [Fig.4] illustrates a flowchart of the different steps of a method for processing at least part of the connected vehicles of [Fig.l], according to a particular and non-limiting exemplary embodiment of the present invention. Description of examples of implementation

[0031] A method and a device for controlling a vehicle data processing system connected to a wireless communication network will now be described in the following with joint reference to Figures 1 to 4. The same elements are identified with the same reference signs throughout the description which follows.

[0032] The terms "first(s)", "second(s)" (or "first(s)", "second(s)"), etc. are used in this document by arbitrary convention to enable different elements (such as operations, means, etc.) implemented in the embodiments described below to be identified and distinguished. Such elements may be distinct or correspond to a single element, depending on the embodiment.

[0033] According to a particular and non-limiting example of embodiment of the present invention, the processing of vehicle data obtained from a sample of vehicles connected to a wireless communication network is for example implemented by a data processing device of the server or computer type connected in communication via a wireless connection to a group of connected vehicles comprising the sample. In the following, a connected vehicle corresponds to a vehicle configured to communicate data to the data processing device via a wireless communication network. wireless communication to which the data processing device is connected.

[0034] For this purpose, the group of connected vehicles is selected from a set of vehicles according to a set of first selection criteria, at least one first selection criterion corresponding to an intrinsic vehicle characteristic. The group of connected vehicles thus corresponds to a subset of the set of vehicles comprising only connected vehicles.

[0035] A set of samples comprising one or more samples of connected vehicles is / are selected from the group of connected vehicles according to second selection criteria (which comprise for example the number of samples to be selected from the group, the number of connected vehicles included in each sample and / or the selection method). A sample of connected vehicles thus corresponds to a subgroup of the group of connected vehicles.

[0036] Representative usage data is received from each connected vehicle of the group of connected vehicles, this usage data of each connected vehicle being collected over a time period of a determined duration (for example 1, 2 or 3 months).

[0037] A set of parameters is determined for each connected vehicle of the group of connected vehicles from the usage data of each connected vehicle received. A plurality of values ​​are determined for each of these parameters at different time instants of the time period during which the usage data was collected.

[0038] One or more values, called first statistical values, are determined for each parameter and associated with the group of connected vehicles, this or these first statistical values ​​being determined by statistical processing of the pluralities of values ​​determined for each connected vehicle of the group of connected vehicles. In the same way, one or more values, called second statistical values, are determined for each parameter and associated with each sample of the set of samples, this or these second statistical values ​​being determined by statistical processing of the pluralities of values ​​determined for each connected vehicle of each sample with which they are associated.

[0039] An error is determined for each sample by comparing the second statistical values ​​to the first statistical values. A sample is then selected from the set of samples based on the error determined for each sample. The selected sample corresponds, for example, to the one with the lowest error.

[0040] Such a method makes it possible to select the most representative sample of vehicles from a larger group of vehicles, for example to then collect, via a wireless connection, data representative of the use of one or more of the components of the vehicles in the selected sample.

[0041] [Fig.l] schematically illustrates a communication environment 1 of a group 11 of vehicles connected to a wireless communication network, according to a particular and non-limiting exemplary embodiment of the present invention.

[0042] Each vehicle of group 11 of connected vehicles corresponds for example to a vehicle with a thermal engine, with electric motor(s) or even a hybrid vehicle with a thermal engine and one or more electric motors. Each vehicle thus corresponds for example to a land vehicle, for example a car, a truck, a bus, a motorcycle.

[0043] The group 11 of connected vehicles corresponds to a subset of a larger set of vehicles, the connected vehicles being selected from the set of vehicles according to a set of first selection criteria, as described below.

[0044] Each vehicle of the group 11 is said to be connected in that it carries a communication system configured to communicate with one or more remote devices 101 via an infrastructure of a wireless communication network. The remote device 101 advantageously corresponds to a device configured to process data, for example data stored in the memory of the remote device 101 and / or data received from the connected vehicles forming the group 11 of connected vehicles. The remote device 101 corresponds for example to a server or a computer of the “cloud” 100.

[0045] The communication system of a connected vehicle comprises, for example, one or more communication antennas connected to a telematic control unit, called TCU (from the English "Telematic Control Unit"), itself connected to one or more computers of the on-board system of the connected vehicle. The antenna(s), the TCU unit and the computer(s) form, for example, a multiplexed architecture for the realization of different services useful for the proper functioning of the connected vehicle and for assisting the driver and / or passengers of the connected vehicle in the control of the connected vehicle and / or for establishing a diagnosis on the functioning of one or more components of the connected vehicle.The computer(s) and the TCU communicate and exchange data with each other via one or more computer buses, for example a communication bus of the CAN (Controller Area Network), CAN FD (Controller Area Network Flexible Data-Rate), FlexRay (according to the ISO 17458 standard) or Ethernet (according to the ISO / IEC 802-3 standard) data bus type.

[0046] The mobile communication infrastructure enabling wireless data communication between a connected vehicle of group 11 and the remote device 101 comprises for example one or more communication devices 102 of the relay antenna type (cellular network) or roadside unit, called UBR. In a communication mode using such a network architecture, the data are for example transmitted by the vehicle connected to the remote device 101 of the “cloud” 100 via a relay antenna 102 (the antenna 102 being for example connected to the “cloud” 100 via a wired link and the remote device 101 itself being connected to the network infrastructure of the “cloud” 100 via a wired and / or wireless network).

[0047] The wireless communication system allowing the exchange of data between the connected vehicle and the remote device 101 corresponds for example to: - a vehicle-to-infrastructure V2I communication system (from English “vehicle-to-infrastructure”), for example based on the 3GPP LTE-V or IEEE 802.1 Ip standards of ITS G5; or - a cellular network type communication system, for example an LTE (Long-Term Evolution) or LTE-Advanced (LTE-Advanced) type network, also called LTE 3G, 4G or 5G; or - a Wifi type communication system according to IEEE 802.11, for example according to IEEE 802.1 In or IEEE 802.1 lac.

[0048] A process of communication and / or processing of data from vehicles connected to the wireless communication network, particular embodiments of which are described with regard to [Fig. 2], is advantageously implemented by a data processing device such as the remote device 101.

[0049] In a first operation 21 of the process, the group 11 of vehicles connected to the wireless network via a wireless connection is selected from a set of vehicles comprising more vehicles than the group 11 based on a set of first selection criteria 210. At least one first selection criterion of the set of first criteria 210 corresponds to an intrinsic vehicle characteristic.

[0050] The set of vehicles groups together, for example, vehicles identified on one or more databases, for example one or more databases identifying the customers of a car manufacturer.

[0051] The set of vehicles includes, for example, vehicles in circulation, i.e. vehicles used by their owners.

[0052] Each vehicle in the set is identified by a unique identifier, for example the VIN number (from the English “Vehicle Identifier Number” or in French “Numéro d'identification de véhicule”) or any other identifier. The database comprises for example a set of characteristics associated with each vehicle and linked to each vehicle via its identifier, the characteristics being for example stored in one or more look-up tables, called LUTs (from the English “Look-Up table”).

[0053] The characteristics associated with each vehicle in the set include: - intrinsic characteristics of the vehicle such as, for example, the vehicle model, the vehicle's engine (for example, electric, thermal or hybrid engine), the vehicle's engine power, the vehicle's mass, the weight / power ratio, the first date of entry into service, the level of equipment, the type of vehicle (utility, van, car, estate, sedan, SUV, etc.), the size of the vehicle, the AD AS (Advanced Driver-Assistance System) functions and / or systems fitted to the vehicle, the vehicle's level of autonomy, the serial number of all or part of the vehicle's organs or components, etc.; - extrinsic characteristics of the vehicle such as, for example, the geographical area (region, country, continent) where the vehicle was sold or circulated, the number of times the vehicle has changed owners, the type of owner (individual, company, vehicle rental agency, shared vehicle), etc.

[0054] The set of first selection criteria is for example determined according to the population of vehicles on which a study or analysis must be carried out, for example a study relating to the actual use of the vehicles in the field.

[0055] The set of first criteria advantageously comprises at least one intrinsic characteristic of the vehicle, for example the type of engine (for example an electric vehicle, called BEV (from the English “Battery Electric Vehicle” or in French “Véhicule électrique à batterie”)), the model of the vehicle, a type of component(s) or function(s) or on-board AD AS system(s), etc.

[0056] If the set of vehicles from which the group 11 of vehicles is selected comprises connected vehicles and non-connected vehicles, then a first selection criterion corresponds to connected vehicle to select only connected vehicles.

[0057] The set of first criteria further comprises, for example, one or more intrinsic characteristics, for example the database(s) to be requested, the geographical area, the number of connected vehicles to be selected to form the group 11, etc.

[0058] If all the connected vehicles are identified in one (or more) particular databases, then a first criterion corresponds to the database(s) to be used to select it in order to only make the selection in the database(s) comprising only connected vehicles.

[0059] A query comprising the set of first selection criteria is generated and executed on the device(s) storing the desired database(s).

[0060] The group 11 of selected connected vehicles is for example identified by the list of unique identifiers of the connected vehicles included in the group 11 and obtained from the query(s) performed on the database(s).

[0061] In a second operation 22 of the process, a set of samples of connected vehicles is selected from the group 11 of connected vehicles based on a set of second selection criteria 220.

[0062] A sample corresponds to a subgroup of group 11 and advantageously comprises a plurality of connected vehicles.

[0063] According to the example illustrated in [Fig. 1], 2 samples 111, 112 of connected vehicles are selected and identified in the group 11 of connected vehicles.

[0064] Each sample 111, 112 comprises a list of connected vehicles each identified via its unique identifier.

[0065] The set of second selection criteria 220 comprises: - a number of samples forming the sample set, for example 2, 3, 5, 7 or 10 samples; and / or - a number of connected vehicles included in each sample of the sample set, for example 50, 100, 200, 500 or 1000 vehicles per sample; and / or - a type of selection of connected vehicles forming each sample from a random selection and a deterministic selection (this is according to determined selection rules, for example disjoint samples).

[0066] The connected vehicles included in each sample 111 and 112 are for example randomly selected from group 11, with the instruction that each one includes the same number of connected vehicles (for example 500 or 1000 connected vehicles in each sample 111, 112).

[0067] In a third operation 23 of the process, data representative of the use of each connected vehicle of the group 11 are collected, i.e. received by the remote device 101 from each connected vehicle of the group 11. These data of use of the connected vehicles are collected over a determined time period, for example over a period of a duration equal to a few weeks or a few months.

[0068] For this purpose, one or more requests are transmitted by the remote device 101 to each connected vehicle of the group 11 via the wireless network infrastructure to receive in return the usage data (either after each request or periodically, depending on the request). The request includes for example data representative of the type of usage data that each connected vehicle must send back to the remote device 101, and at what frequency or periodicity.

[0069] The usage data of each connected vehicle of group 11 includes, for example, by way of illustration: - the distance traveled by the vehicle, in km, and / or - fault codes recorded by one or more computers, and / or - AD AS system control parameters, and / or - parameters measured for one or more components (for example the temperature measured in a battery or in the engine), - a number of charge / discharge cycles of a traction battery, and / or - an average speed, and / or - a duration of use of the vehicle and / or a duration of parking, and / or - a number of engine stops / starts, and / or - a temperature of the external environment in which the vehicle is traveling, and / or - a type of road environment used (urban, highway, etc.), etc.

[0070] Usage data corresponds to all data relating to the use of the vehicle and its components.

[0071] The usage data is processed to determine, for each connected vehicle in the group, a set of parameters.

[0072] For each parameter, several values ​​are determined as a function of the usage data, each value of the plurality being representative of the parameter at a particular time instant in the time period of collection of the usage data. Thus, each parameter of the set is determined at different time instants as a function of the usage data obtained at these different time instants (or between two consecutive time instants), for example every day, every 2 days or every week, the frequency of determination of the parameter depending for example on the type of the parameter.

[0073] The different values ​​of each parameter of the set of parameters are recorded in a storage device (a memory) included in the remote device 101 or connected in communication to the remote device 101. Each stored value is for example time-stamped to distinguish the different determinations of the same parameter.

[0074] The same parameters are determined according to the same functions or calculation rules for each connected vehicle of group 11, in order to be able to compare different vehicles with each other while considering the same parameters.

[0075] In a fourth operation 24 of the process, one or more values, called first statistical values, relating to the group 11 of connected vehicles are determined for each parameter of the set of parameters by statistical processing of the pluralities of values ​​determined for each connected vehicle of the group 11.

[0076] A statistical treatment corresponds to a type of treatment of calculation of the average of the different values ​​determined for the same parameter during the period determined time period, weighted average type processing, processing of the type determining the minimum value, the maximum value among the different values, determining a histogram of the values, determining a standard deviation, etc.

[0077] Thus, if N parameters are determined for each vehicle of group 11, N first values ​​noted Cr; (i being an index ranging from 1 to N) are for example determined for group 11 for each time instant by applying a statistical processing of the values ​​obtained for each connected vehicle of group 11 at this time instant. According to this example, the number of first statistical values ​​obtained is equal to N multiplied by the number of values ​​calculated for each parameter.

[0078] According to another example, a first statistical processing is applied to the different values ​​of each parameter then a second statistical processing is applied to the results of the first statistical processing to obtain the first statistical value, for each parameter. According to this other example, N first statistical values ​​Cr; are obtained.

[0079] In the same way, second statistical values ​​are determined for each sample 111, 112 of the set of samples.

[0080] Thus, taking sample 111 as an example, one or more values, called second statistical values, relating to sample 111 (and associated with this sample 111) are determined for each parameter of the set of parameters by statistical processing of the pluralities of values ​​determined for each connected vehicle of sample 111.

[0081] For a given parameter of the set, the statistical processing(s) applied to the values ​​of this parameter to calculate the second associated statistical value are identical to the statistical processing(s) applied to the values ​​of this parameter to calculate the first statistical value (associated with group 11).

[0082] To be able to compare the first statistical values ​​(denoted Cp) with the second statistical values ​​(denoted Ci), for a given parameter, the same statistical treatments are applied to the different values ​​obtained for this parameter. Only the connected vehicles taken into consideration for the calculation of the first and second statistical values ​​vary (i.e. all the connected vehicles of group 11 for the first statistical value and all the connected vehicles of the sample considered 111 or 112 for the second statistical value of the sample considered 111 or 112, respectively).

[0083] The statistical processing(s) applied to the different values ​​of the parameters depend for example on the population of connected vehicles considered, i.e. the type of connected vehicles selected from the set of vehicles according to of the set of first selection criteria.

[0084] In a fifth operation 25 of the process, an error function is applied to the first statistical values ​​and to the second statistical values, for each sample 111, 112, to determine an error between each sample 111, 112 on the one hand and the group 11 on the other hand.

[0085] The error function applied to the first statistical values ​​and to the second statistical values ​​depends for example on the population of connected vehicles considered and / or the statistical processing applied to the parameters.

[0086] As an example, according to a particular embodiment, the error for a sample is calculated with the following function:

[0087] [Math.l] Err= Q)2 with N the number of parameters in the parameter set, Wi a weighting factor associated with the index parameter i, Cr; the first statistical value associated with the index parameter i, and Ci the second statistical value associated with the index parameter i.

[0088] In a sixth operation 26, a sample is selected from the set of samples 111, 112 based on the error associated with each sample.

[0089] The selection of the sample from the set of samples is for example obtained by minimizing the error function.

[0090] The selected sample corresponds for example to the sample whose error is the smallest among the set of calculated errors. Thus if Enjn corresponds to the error calculated for sample 111 (with respect to group 11) and if Enjn corresponds to the error calculated for sample 112 (with respect to group 11), the selected sample corresponds to the one for which the error verifies the following function:

[0091] Min (Errni,Enj12)

[0092] Selecting the sample with the lowest error makes it possible to select the most representative sample of group 11, that is to say the sample whose connected vehicles that make up this sample are the most representative of the set of connected vehicles making up group 11.

[0093] According to a particular embodiment, the sixth operation 26 further comprises a comparison of each calculated error, i.e. each error Enjn and Errm according to the example of [Fig.l], with a determined threshold value. According to an alternative embodiment, only the smallest error among the set of errors Enjn and Enjn is compared to the threshold value.

[0094] According to this embodiment, the sample having the lowest associated error is selected (for example sample 111 if Enjn < Enjn) only when the error lowest associated value (Enjn according to the example) is lower than the determined threshold value.

[0095] If no error among the errors associated with the samples (i.e. Enjn and Err 112 according to the example of [Fig.l]) is less than the threshold value (or if all the calculated errors are greater than the threshold value), then the process loops back to operation 22 for a selection of a new set of samples in group 11.

[0096] The selection of the new set of samples is for example implemented according to a set of third selection criteria. The set of third criteria is for example identical to the set of second criteria (i.e. with the same number of samples, the same number of vehicles connected per sample and a type of selection corresponding to a random selection of the vehicles connected in the group 11 to form each sample).According to a variant, the set of third criteria is different from the set of second criteria (one or more criteria may however be identical, for example the same number of samples but a different number of vehicles in each sample and a different type of selection, for example by introducing a selection with one or more rules (deterministic selection, for example according to an artificial intelligence algorithm for which the selection rules have been learned from training data to improve the selection of connected vehicles forming a sample)).

[0097] When a new set of samples is selected to replace the samples selected in the previous iteration (i.e. to replace samples 111 and 112), operations 23 to 26 following operation 22 are reiterated using the new set of samples (and in particular the usage data of the connected vehicles forming these new samples).

[0098] In a seventh operation 27 of the process, the sample selected in the sixth operation 26, if any (for example sample 111), is used.

[0099] For example, one or more requests are transmitted by the remote device 101 to each connected vehicle of the selected sample 111 to obtain usage data from each connected vehicle (or data relating to a particular component or a particular function or AD AS system). This usage data is for example collected periodically (for example every week or every month) by the remote device 101 from each connected vehicle of the selected sample, and this for a determined period (6 months, 1 year, 2 years) or until the end of life of the vehicle (with prior obtaining of the agreement of the owner of each connected vehicle).

[0100] The collected usage data is for example used to learn one or several learning models (according to any machine learning method known to those skilled in the art), for example a component lifecycle prediction model or a component or system failure prediction model. The usage data form a robust and reliable learning data set since it reflects real-life use of connected vehicles, and this for the most representative sample of a larger group of connected vehicles.

[0101] Using data from a sample rather than data from the group as a whole reduces the bandwidth requirements for collecting the data via the wireless network and also reduces the computing resource requirements for processing the usage data by the remote device 101.

[0102] According to another exemplary embodiment, the usage data of the sample 111 (collected during the time period determined as described above and / or the usage data collected after the selection of the sample 111) are used for the dimensioning and development of vehicle components, systems or parts, more particularly for carrying out mission profile calculations necessary for the dimensioning of the components.

[0103] [Fig. 3] schematically illustrates a device 3 configured for communication and / or processing of data from vehicles connected to a wireless communication network, according to a particular and non-limiting exemplary embodiment of the present invention. The device 3 corresponds for example to a computing device or a data processing device such as the remote device 101, for example a computer or a server.

[0104] According to an alternative embodiment, the device 3 corresponds to a device on board the vehicle 10, for example a computer or a telematic control unit, called TCU (from the English “Telematic Control Unit”).

[0105] The device 3 is for example configured for the implementation of the operations described with regard to figures 1 and 2 and / or the steps of the method described with regard to [Fig.4]. Examples of such a device 3 include, but are not limited to, a computer, a laptop, a server, on-board electronic equipment such as an on-board computer of a vehicle, an electronic calculator such as an ECU (“Electronic Control Unit”), a smartphone, a tablet. The elements of the device 3, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and / or in discrete components. The device 3 can be produced in the form of electronic circuits or software (or computer) modules or even a combination of electronic circuits and software modules.

[0106] The device 3 comprises one (or more) processor(s) 30 configured to execute instructions for carrying out the steps of the method and / or for executing the instructions of the software(s) embedded in the device 3. The processor 30 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The device 3 further comprises at least one memory 31 corresponding for example to a volatile and / or non-volatile memory and / or comprises a memory storage device which may comprise volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

[0107] The computer code of the embedded software(s) comprising the instructions to be loaded and executed by the processor is for example stored in the memory 31.

[0108] According to various particular and non-limiting embodiments, the device 3 is coupled in communication with other similar devices or systems and / or with communication devices, for example a TCU (from the English “Telematic Control Unit” or in French “Telematic Control Unit”), for example via a communication bus or through dedicated input / output ports.

[0109] According to a particular and non-limiting exemplary embodiment, the device 3 comprises a block 32 of interface elements for communicating with external devices. The interface elements of the block 32 comprise one or more of the following interfaces: - RF radio frequency interface, for example Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or Bluetooth® type (according to IEEE 802.15.1), in the 2.4 GHz frequency band, or Sigfox type using UBN (Ultra Narrow Band) radio technology, or LoRa in the 868 MHz frequency band, LTE (LTE) “Long-Term Evolution” or in French “Long-Term Evolution”), LTE-Advanced (or in French LTE-advanced); - USB interface (from the English “Universal Serial Bus” or “Universal Serial Bus” in French); - HDMI interface (from the English “High Definition Multimedia Interface” or “High Definition Multimedia Interface” in French); - LIN interface (from the English “Local Interconnect Network”).

[0110] According to another particular and non-limiting exemplary embodiment, the device 3 comprises a communication interface 33 which makes it possible to establish communication with other devices (such as other computers of the on-board system) via a communication channel 330. The communication interface 33 corresponds for example to a transmitter configured to transmit and receive information and / or data via the communication channel 330. The communication interface 33 corresponds, for example, to a wired network of the Ethernet type (standardized by the ISO / IEC 802-3 standard).

[0111] According to a particular and non-limiting exemplary embodiment, the device 3 can provide output signals to one or more external devices, such as a display screen 340, touch-sensitive or not, one or more speakers 350 and / or other peripherals 360 (projection system) via output interfaces 34, 35 and 36 respectively. According to a variant, one or other of the external devices is integrated into the device 3.

[0112] [Fig. 4] illustrates a flowchart of the different steps of a method for processing data from vehicles connected to a wireless communication network, according to a particular and non-limiting exemplary embodiment of the present invention. The method is for example implemented by a computing device or a data processing device such as the remote device 101, for example a computer or a server, or by the device 3 of [Fig. 3].

[0113] In a first step 41, a group of vehicles connected to the wireless network via a wireless connection is selected from a set of vehicles based on a set of first selection criteria, at least one first selection criterion of the set corresponding to an intrinsic vehicle characteristic.

[0114] In a second step 42, a set of samples of connected vehicles is selected from the group of connected vehicles based on a set of second selection criteria.

[0115] In a third step 43, data representative of the use of each connected vehicle are received from each connected vehicle of the group via the wireless connection over a determined time period.

[0116] In a fourth step 44, a set of parameters is determined, for each connected vehicle of the group, from the data representative of use of each connected vehicle, a plurality of values ​​being determined at different time instants of the time period determined for each parameter of the set of parameters.

[0117] In a fifth step 45, at least one first statistical value is determined for the group of connected vehicles, for each parameter of the set of parameters, by statistical processing of the pluralities of values ​​determined for each connected vehicle of the group of connected vehicles.

[0118] In a sixth step 46, at least one second statistical value is determined for each sample of the set of samples, for each parameter of the set of parameters, by statistical processing of the pluralities of values ​​determined for each connected vehicle of each sample.

[0119] In a seventh step 47, an error is determined for each sample by comparing the second statistical values ​​to the first statistical values.

[0120] In an eighth step 48, a sample is selected from the set of samples based on the error associated with each sample.

[0121] According to a variant, the variants and examples of the operations described in relation to one of figures 1 and 2 apply to the steps of the method of [Fig.4].

[0122] Of course, the present invention is not limited to the exemplary embodiments described above but extends to a method for learning a model for predicting the life cycle or failure of a vehicle component based on learning data obtained from connected vehicles of a sample of vehicles without thereby departing from the scope of the present invention. The same would apply to a device configured for implementing such a method.

[0123] The present invention also relates to a system comprising the device 3 of [Fig.3] connected in wireless communication to a group 11 of connected vehicles.

Claims

Claims

1. Method for processing data from vehicles connected to a wireless communication network, said method comprising the following steps: a) selecting (41), from a set of vehicles, a group (11) of vehicles connected to said wireless network via a wireless connection as a function of a set of first selection criteria, at least one first selection criterion of said set corresponding to an intrinsic vehicle characteristic; b) selecting (42), from said group (11) of connected vehicles, a set of samples (111, 112) of connected vehicles as a function of a set of second selection criteria; c) receiving (43), from each connected vehicle of said group (11) via the wireless connection, data representative of the use of each connected vehicle over a determined time period;d) determining (44), for each connected vehicle of said group (11), a set of parameters from said data representative of use of each connected vehicle, a plurality of values ​​being determined at different time instants of said time period determined for each parameter of said set of parameters; e) for each parameter of said set of parameters, determining (45) at least one first statistical value for said group of connected vehicles by statistical processing of the pluralities of values ​​determined for each connected vehicle of said group (11) of connected vehicles; f) for each parameter of said set of parameters, determining (46) at least one second statistical value for each sample of said set of samples (111, 112) by statistical processing of the pluralities of values ​​determined for each connected vehicle of each sample;g) for each sample, determining (47) an error by comparing the second statistical values ​​to the first statistical values; and h) selecting (48) a sample from the set of samples (111, 112) based on the error associated with each sample.;

2. Method according to claim 1, for which said error, noted Err, is determined via the following function: Err _ VN -CT with N 'c number of parameters in the set of parameters, Wi a weighting factor associated with the index parameter i, Cr; the first statistical value associated with the index parameter i, and Ci the second statistical value associated with the index parameter i.

3. A method according to claim 1 or 2, wherein the selected sample corresponds to the sample having the lowest associated error.

4. The method of claim 3, wherein said selecting (48) a sample further comprises comparing the error associated with the selected sample to a determined threshold value, said sample having the lowest associated error being selected only when said lowest associated error is less than said determined threshold value.

5. A method according to claim 4, wherein, when said lowest associated error is greater than said determined threshold value, said method further comprises the following steps: - selecting a new set of samples from said group of connected vehicles based on a set of third selection criteria; and - repeating steps f) to h) by replacing said set of samples (111, 112) with the new set of samples.

6. Method according to one of claims 1 to 5, for which said set of second selection criteria comprises: - a number of samples forming said set of samples; and / or - a number of connected vehicles included in each sample of said set of samples; and / or - a type of selection of the connected vehicles forming each sample from a random selection and a deterministic selection.

7. Method according to one of claims 1 to 6, further comprising a step of training a life cycle prediction model of at least one vehicle component from training data received from each connected vehicle of the selected sample via the wireless connection, said training data comprising the representative usage data of each connected vehicle of the selected sample.

8. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor.

9. Device (3) for processing data from vehicles connected to a wireless communication network, said device (3) comprising a memory (31) associated with at least one processor (30) configured for implementing the steps of the method according to any one of claims 1 to 7.

10. A system comprising the device of claim 9 and a group (11) of vehicles connected to said device via a wireless connection.

Images