DE102020129563B4 - Method for initiating a component improvement measure of a vehicle component of a motor vehicle, computing device and motor vehicle with a computing device - Google Patents

Abstract

Method for initiating a component improvement measure of a vehicle component of a motor vehicle (34), with the steps: a) sending (S10) a request to initiate the component improvement measure; b) determining (S12) a current vehicle equipment (11) and a compatibility parameter (10) of the motor vehicle by a computing device (36) according to the sent request, wherein the compatibility parameter (10) determines which vehicle components are compatible with the motor vehicle; c) retrieving (S14) a vehicle component selection from at least one vehicle-external storage device by the computing device (36), wherein the vehicle component selection is filtered from all vehicle components of the vehicle-external storage device at least depending on the current vehicle equipment (11) and the compatibility parameter (10); , 14) are analyzed to determine suitable vehicle components, with the analysis determining a separate data profile (16, 19, 22, 28, 30) for each of the data sources (13, 14), the respective vehicle components of the vehicle component selection depending on the respective A respective point value (17, 20, 23, 29, 31) is assigned to the data profile (16, 19, 22, 28, 30), each point value (17, 20, 23, 29, 31) additionally being determined by means of a value specified by the data source Weighting factor (33) is weighted, the weighting factor (33) indicating how important the data source (13, 14) is for assessing the necessity of the vehicle component; e) combining (S18) the respective weighted point values of the respective vehicle component to form a ranking value of the respective one Vehicle component by the computing device (36);f) providing (S20) a selection list of the vehicle components for the motor vehicle by the computing device (36), the vehicle components on the selection list being sorted depending on the respective rank value;g) selection (S22) of a vehicle component from the selection list and initiating the component improvement measure, with an exchange or installation of the selected vehicle component being carried out as a component improvement measure; wherein the data sources comprise at least one vehicle data source (15), vehicle sensor data of the motor vehicle being measured for the vehicle data source, a driving profile (16) of the motor vehicle (34) being determined from the vehicle sensor data and the point values (17) of the vehicle data source (15) being determined in Dependency of the driving profile (16) can be assigned.

Description

The invention relates to a method for initiating a component improvement measure of a vehicle component of a motor vehicle, a computing device that is designed to carry out the method and a motor vehicle with such a computing device.

Today there are a large number of motor vehicles that can have different equipment variants with different vehicle components, whereby vehicle components can include, for example, electronic and/or mechanical components, such as radios, infotainment systems, driver assistance systems, tires, brakes or tuning components. Users who are looking for new or improved vehicle components for their motor vehicle, i.e. who want to carry out a vehicle component improvement measure, have had to search through a large number of different offers and websites until they have found a suitable vehicle component to improve the motor vehicle.

Searching for vehicle components independently for the component improvement measure has the disadvantage that a lot of time is lost in the search for the appropriate vehicle component, with the most suitable vehicle components possibly being overlooked. Furthermore, vehicle components can be incompatible with the motor vehicle due to incorrect selection, which can lead to complex replacement measures.

From the US 2018 / 0 260 874 A1 discloses a method, a computer-readable storage medium and a system, the system comprising a plurality of partner and associated websites in network communication and operating under an overarching granular community specialty website.

From the WO 2016/ 191 078 A1 is a computer-implemented method for recommending items for future purchase by a consumer based on the consumer's historical actions.

From the US 2012 / 0 035 969 A1 A computer-implemented contextual recommendation receiving method, system and device are known which enable receipt of suggestions, the suggestions being based on derived preferences.

From the US 2016 / 0 078 403 A1 A system and method for recommending and procuring parts to repair a defective vehicle are known.

From the US 9,665,900 B1 Systems and methods are known that determine sales rankings for parts based on one or more metrics.

From the US 2018 / 0 150 776 A1 Methods and systems are known that receive data at least partially associated with one or more vehicle-related products/services, determining one or more predictions associated with the one or more vehicle-related products/services.

The object of the present invention is to simplify a component improvement measure for a user.

This task is solved by the independent patent claims. Advantageous developments of the invention are disclosed in the dependent claims, the following description and the figures.

The invention provides a method for initiating a component improvement measure of a vehicle component of a motor vehicle. A vehicle component can, for example, include an electronic device in the motor vehicle, for example a control unit or an infotainment system, as well as mechanical components such as brakes, tires, a cooling system and/or performance and torque improvement measures. A component improvement measure can be understood as replacing or installing the vehicle component in the motor vehicle. The method, which can be carried out by a computing device, for example, includes as step a) sending a request to initiate the component improvement measure, as step b) determining a current vehicle equipment and a compatibility parameter of the motor vehicle, the compatibility parameter determining which vehicle components are compatible with the motor vehicle and as step c) retrieving a vehicle component selection from at least one vehicle-external storage device, the vehicle component selection being filtered from all vehicle components of the vehicle-external storage device at least depending on the current vehicle equipment and the compatibility parameter. In other words, the component improvement measure can be started by a request, in which case it can then be determined which vehicle equipment the motor vehicle currently has and which vehicle components can be installed in the motor vehicle. For this purpose, a compatibility parameter of the motor vehicle can be determined, which can indicate which vehicle components fit the motor vehicle. The vehicle equipment can be carried out, for example, by retrieving a vehicle memory, in which it can be stored which vehicle equipment the motor vehicle currently has. However, the current vehicle equipment can also be queried by a manufacturer of the motor vehicle, in particular a manufacturer database. Alternatively or additionally, the current vehicle equipment can also be entered in the request to initiate the component improvement measure by a user. Based on the current vehicle equipment and the compatibility parameter, a vehicle component selection can be loaded from at least one vehicle-external storage device, preferably from several vehicle-external storage devices, wherein all vehicle components stored on the vehicle-external storage device or devices can be pre-filtered using the vehicle equipment and the compatibility parameter. This means that, for example, vehicle components that correspond to the current vehicle equipment are not taken into account for the vehicle component selection. Furthermore, all vehicle components that are not compatible with the motor vehicle can be filtered out from the vehicle component selection. For example, it can be checked for each vehicle component whether it matches the compatibility parameter, whereby a respective vehicle component can be assigned to the vehicle component selection if it matches the compatibility parameter. Preferably, a category of vehicle components, which can be specified by a user, can also be taken into account for the vehicle component selection. The category can, for example, indicate the application area for which a vehicle component is being sought. The vehicle-external storage device from which the vehicle component selection can be retrieved can be, for example, a server, in particular from a manufacturer of the motor vehicle and/or a third-party provider.

Furthermore, the method includes, as step d), carrying out a weighting process, wherein in order to carry out the weighting process, predetermined data sources are analyzed to determine suitable vehicle components, with the analysis determining a separate data profile for each of the data sources, the respective vehicle components of the vehicle component selection depending on the A respective point value is assigned to the respective data profile, each point value being additionally weighted by means of a weighting factor specified by the data source, as step e) combining the respective weighted point values of the respective vehicle component to form a rank value of the respective vehicle component, as step f) providing a selection list the vehicle components for the motor vehicle, the vehicle components on the selection list being sorted depending on the respective rank value and as step g) selecting a vehicle component from the selection list and initiating the component improvement measure. In other words, a weighting process is carried out on the vehicle component selection, with predetermined data sources being analyzed to determine suitable vehicle components. A data profile can be created through the analysis, which can preferably be carried out using an algorithm, in particular artificial intelligence. In particular, each data source can include data from which, for example, a driver's behavior, a prediction about wear parts and/or a change in environmental conditions, such as the weather, can be carried out in order to conclude which vehicle component may be required. The data profile can therefore have a prediction or user behavior derived from the data source, wherein vehicle components can be associated with the prediction and/or the user behavior. Preferably, there may be different data sources that cover different areas. Based on the data profile of the respective data sources, point values can then be assigned to each vehicle component, whereby the respective vehicle component can receive a point value from each determined data profile. This means that, for example, a first data profile can be created using a first data source and a second data profile can be created using a second data source. A vehicle component can then receive a first point value depending on the first data profile and a second point value depending on a second data profile. Accordingly, the other vehicle components of the vehicle component selection can receive point values.

For example, a data source can include vehicle data, whereby it can be determined from the vehicle data, for example, that the motor vehicle covers long distances, which can be stored in the data profile of the vehicle data, whereby the data profile of the vehicle data can be referred to, for example, as a driving profile. In this case, for example, an algorithm can determine that vehicle components that are at a high vehicle Performance is required, such as brake pads or tires, receives a high point value.

Further data sources that allow a conclusion to be drawn as to whether a vehicle component is required by the motor vehicle or a user of the motor vehicle can be, for example, weather data sources, traffic data sources or data sources that include a location and/or a season. The respective data sources can be present, for example, in the motor vehicle or a data network, in particular the Internet.

It is preferably provided that each data source is additionally weighted by weighting a respective point value of the vehicle component using a weighting factor predetermined by the data source. This means that the weighting factor can be used to weight how important the data source is for assessing the necessity of the vehicle component. For example, a data source for vehicle data can be weighted higher than a data source for weather data, since the data source for vehicle data can allow a more precise conclusion to be drawn about driving behavior. For example, a data source weighting factor for vehicle data can have a value of 35 percent and a value for weather data only 5 percent. This means that each point value of the respective vehicle components that were assigned by a first data source can be weighted using a first value and all point values of the vehicle components that were determined by a second data source can be weighted using a second value. The multiple weighted point values of a respective vehicle component can then be combined to form a rank value, wherein the rank value can preferably be a sum of the respective weighted point values of the respective vehicle component. In other words, a vehicle component is initially assigned several point values, in particular one from each data source, whereby the point values can be different for each data source. Each point value can then be weighted depending on the relevance of the data source, and the weighted point values of the vehicle component can finally be combined with one another, in particular summed, to obtain a rank value for the vehicle component.

Using the rank value, the vehicle component can then be positioned in a selection list, with preferably the vehicle components with descending rank value being entered into the selection list. Finally, a vehicle component can be selected from the selection list and the component improvement measure can be initiated. The selection may, for example, be carried out by a user or automatically according to the ranking value and the component improvement measure may, for example, include installation of the selected vehicle component.

Furthermore, it is provided that the data sources include at least one vehicle data source, vehicle sensor data of the motor vehicle being measured for the vehicle data source, a driving profile of the motor vehicle being determined from the vehicle sensor data and the point values being assigned to the vehicle data source depending on the driving profile. In other words, a driving profile of the motor vehicle and/or a user of the motor vehicle can be determined from the measured vehicle sensor data, with the driving profile being able to achieve a more precise assignment of the point values of the vehicle data source. For example, a driving style can be determined via the driving profile and vehicle components that are adapted to the driving style can be rated by the algorithm with a higher point value than vehicle components that do not fit the driving profile. For example, the vehicle data source can be accessed via a vehicle diagnostic system (OBD, OBD2). This results in the advantage that actual use of the motor vehicle can be used to determine the vehicle component.

The invention has the advantage that a user can quickly find the vehicle components that are right for him, which means that time can be saved when carrying out the component improvement measure. Furthermore, user satisfaction can be increased since incorrect selection of the vehicle component due to vehicle incompatibility is eliminated. Furthermore, costs for a manufacturer or third-party provider can also be reduced, since fewer incorrect purchases are made by a user and this means that there is no need to exchange and/or convert the motor vehicle. Overall, the method can improve the component improvement measure.

The invention also includes embodiments that result in further advantages.

One embodiment provides that the determination of the current vehicle equipment and the compatibility parameter is carried out by means of a data retrieval depending on a vehicle identification number. In other words, the vehicle identification number can be known, through which the current vehicle equipment can be called up in a database. In particular, a vehicle equipment can also be known from a history of a previously carried out procedure for selecting and initiating the component improvement measure. In this way, vehicle components newly added to a basic equipment can also be known. This embodiment has the advantage that the current vehicle equipment and the compatibility parameter for the motor vehicle can be easily determined.

A further embodiment provides that the current vehicle equipment is recognized and provided by a control unit of the motor vehicle for the determination in step b). In other words, a control unit of the motor vehicle can determine which vehicle components are currently present in the motor vehicle, and this data can be retrieved by the control unit. This embodiment has the advantage that newly added vehicle components, which cannot be stored in a manufacturer database, for example, are recognized, whereby the filtering for the vehicle component selection can be improved.

A further embodiment provides that static and dynamic data sources are analyzed to carry out the weighting process. Static data sources mean data sources that include static data about the motor vehicle and/or a user of the motor vehicle that do not or hardly change over time. For example, the static data sources may include information about a type of motor vehicle and user information such as a place of residence. Dynamic data sources mean data sources that include dynamic data that can change, in particular over time, depending on the use of the motor vehicle. For example, dynamic data sources may include data about vehicle usage, weather, or sales data. This embodiment has the advantage that many different data sources are taken into account for the weighting process.

It is particularly preferably provided that the data sources include at least one user data source, with a selection behavior of users of the method being measured for the user data source, a swarm profile being determined from the selection behavior of the users and the point values being assigned to the user data source depending on the swarm profile. This means that one or more vehicle components can be assigned a higher point value using swarm intelligence, whereby, for example, the swarm profile can show which vehicle components are particularly popular and are often selected. This allows the selection of vehicle components to be further improved based on the behavior of other users.

In a further advantageous embodiment, it is provided that the data sources comprise at least one weather data source and/or metadata of the sent request, wherein weather data is measured for the weather data source, wherein a weather forecast profile is created from the weather data, wherein location information and/or time information is determined from the metadata, wherein the point values are assigned depending on the weather forecast profile and/or the location and/or time information determined from the metadata. In other words, a weather forecast profile can be determined from weather data, through which the algorithm can take particular account of weather-related vehicle components. For example, it can be known from the weather forecast profile that a heat wave is imminent, in which case the algorithm can assign cooling systems for the motor vehicle and air conditioning systems with a high point value. Alternatively or additionally, metadata from the request sent in step a) can also be analyzed, wherein the metadata includes, for example, an IP address and a time stamp, wherein a location can be deduced from the IP address and a time, in particular a season, can be deduced from the time stamp. From this location and time information, the algorithm can determine, for example, that the request was sent in winter in a snowfall region, which allows the algorithm to assign a higher point value to winter-relevant vehicle components, such as winter tires, if it is determined that the current vehicle equipment does not include winter tires. This embodiment has the advantage that weather and location-dependent data can be taken into account.

A further embodiment provides that the weighting factor of the respective data source is determined by means of a machine learning algorithm, the machine learning algorithm checking to which position of the selection list the vehicle component selected in step g) was sorted by the weighting factor of the respective data source, whereby in Depending on the position of the selected vehicle component, the weighting factors responsible for the positioning are adjusted. In other words, the machine learning algorithm can check itself whether the weighting factor was chosen correctly. For this purpose more can preferably be done Several selection processes by different users are analyzed by the machine learning algorithm as to whether the vehicle components that were weighted by the weighting factor into a ranking position on the selection list are actually selected by the users, the weighting factor being able to be adjusted if determined by the machine learning algorithm that it is more likely that vehicle components will be selected that are not given as high a weight. In particular, the weighting factor can be increased for those data sources that are determined to be in a selection category that is important to the user. This embodiment has the advantage that the weighting process can be continuously improved. In particular, the weighting process can be individually adapted to a respective user.

A further aspect of the invention relates to a computing device which is designed to carry out the method according to one of the preceding embodiments. The computing device can include, for example, a computer, a smartphone, a tablet computer and/or an infotainment system of the motor vehicle. In particular, the computing device can be designed to carry out steps a) to d), whereby the initiation of the component improvement measure can include, for example, a reservation of an appointment for a conversion of the motor vehicle. This aspect results in the same advantages and possible variations as with the process.

According to the invention, a motor vehicle with such a computing device is also provided. The computing device can in particular be integrated into the motor vehicle, for example in the form of an infotainment system. Alternatively or additionally, the computing device can be coupled to the motor vehicle via a wireless data connection, for example WLAN, Bluetooth and/or mobile data communication according to a common mobile communication standard. The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

The invention also includes the control device for the motor vehicle. The control device can have a data processing device or a processor device that is set up to carry out an embodiment of the method according to the invention. For this purpose, the processor device can have at least one microprocessor and/or at least one microcontroller and/or at least one FPGA (Field Programmable Gate Array) and/or at least one DSP (Digital Signal Processor). Furthermore, the processor device can have program code that is designed to carry out the embodiment of the method according to the invention when executed by the processor device. The program code can be stored in a data memory of the processor device.

The invention also includes further developments of the computing device according to the invention, which have features as have already been described in connection with the further developments of the motor vehicle according to the invention. For this reason, the corresponding developments of the method according to the invention are not described again here.

The invention also includes the combinations of the features of the described embodiments. The invention therefore also includes implementations that each have a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

• 1 ein schematisches Verfahrensablaufdiagramm gemäß einer beispielhaften Ausführungsform;
• 2 ein Kraftfahrzeug mit einer Rechenvorrichtung gemäß einer beispielhaften Ausführungsform.

Examples of embodiments of the invention are described below. This shows:

• 1 a schematic process flow diagram according to an exemplary embodiment;
• 2 a motor vehicle with a computing device according to an exemplary embodiment.

The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention that are to be considered independently of one another and which also further develop the invention independently of one another. Therefore, the disclosure is intended to include combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention that have already been described.

In the figures, the same reference numerals designate functionally identical elements.

In 1 1 shows a schematic process flow diagram of a method for initiating a component improvement measure of a vehicle component of a motor vehicle according to an exemplary embodiment. In one In step S10, for example, a user can send a request to initiate the component improvement measure, for example to a computing device that can carry out the subsequent method steps as program steps within the framework of a computer program. The request can be sent, for example, from a smartphone of the user or an infotainment system of the motor vehicle. In particular, the component improvement measure can be used to upgrade or improve a vehicle component of the motor vehicle, for example to facilitate installation of the appropriate vehicle component.

After sending the request to initiate the component improvement measure, a compatibility parameter 10 can be determined in a step S12, whereby the compatibility parameter 10 can be used to check which vehicle components are compatible with the motor vehicle 34. For this purpose, the compatibility parameter 10 can, for example, have a vehicle identification number, through which it can be determined which model, which engine and which tire sizes the motor vehicle 34 has. Furthermore, for example, a current vehicle equipment can be carried out in a sub-step 11 by means of a data retrieval, for example from a manufacturer database, in particular depending on the vehicle identification number. Alternatively or additionally, vehicle information, in particular current vehicle equipment, can be determined manually in a sub-step 12.

Subsequently, in a step S14, a vehicle component selection can be retrieved from at least one vehicle-external storage device, the vehicle component selection representing a selection of all vehicle components that can be stored on the vehicle-external storage device. In particular, all vehicle components of the vehicle-external storage device can be filtered using the current vehicle equipment and the compatibility parameter, so that only vehicle components that fit the motor vehicle and that are not yet installed in the motor vehicle are retrieved.

In a step S16, a weighting process for the vehicle component selection can subsequently be carried out, wherein the weighting process can preferably be an algorithm or program on a computing device 36. To carry out the weighting process, static data sources 13 and dynamic data sources 14 can be analyzed. The aim of the weighting process can be to limit the vehicle component selection to those vehicle components that are required by a user and/or the motor vehicle, for which purpose the data sources 13, 14 can be analyzed to determine which properties may be important for the user/the motor vehicle.

Preferably, a data profile can be determined for each data source in the weighting process, whereby a point value can be assigned to each vehicle component of the vehicle component selection based on the respective data profile. The point value can indicate how well the respective vehicle component fits the data profile of the respective data sources.

For example, the dynamic data sources 14 can include a vehicle data source 15, wherein vehicle sensor data of the motor vehicle can be measured for the vehicle data source and a driving profile 16 can be determined from the vehicle sensor data. For example, an algorithm can determine that the vehicle sensor data shows strong acceleration values, which suggests a sporty driving profile. From this, the algorithm can, for example, determine a high point value for vehicle components that increase performance and torque. In particular, the algorithm can determine point values 17 for respective vehicle components of the vehicle data source 15.

Furthermore, the dynamic data sources 14 can include at least one user data source 18, wherein a selection behavior of users of the method can have been measured for the user data source 18, a swarm profile 19 being able to be determined from the selection behavior of the user and the algorithm being able to determine point values 20 from the swarm profile 19 for vehicle components can be assigned to the user data source. For example, the user data source 18 may include sales data and the swarm profile 19 may include best-selling vehicle components, where the vehicle components that were sold the most can be assigned a high point value 20, for example.

Furthermore, the dynamic data sources 14 can have a weather data source 21 in which measured weather data can be stored, whereby a weather forecast profile 22 can be created from the weather data, for example that a heat wave is imminent. From the weather forecast profile 22, the algorithm can then generate point values 23 for the vehicle components from the weather forecast profile 22. For the For example, in the case of the heat wave, air conditioning systems can be rated with high points 23.

The dynamic data sources 14 can particularly preferably comprise further data sources 24, for example a traffic data source, from which further point values for vehicle components can be calculated.

The static data sources 13 can, for example, include metadata 25 of the sent request to initiate the component improvement measure. For example, location information 26 and time information 27 can be determined from the metadata 25. For example, country-specific properties 28 can be determined from the location information 26, such as a maximum permissible top speed. With this information, the algorithm can then determine point values 29 for the vehicle components based on the location information 26. For example, a current date 30 can be determined from the time information 27 of the metadata 25, whereby the current date 30 can, for example, indicate that the request was sent in a winter time, from which point values 31 for vehicle components can be determined depending on the time information 27. For example, winter-specific items, especially winter tires, can be given a higher point value. Furthermore, the static data source 13 can also include other data sources 32, such as predetermined user data and user preferences.

The point values 17, 20, 23, 29, 31 of the respective data sources 15, 18, 21, 24, 25, 32 determined in this way can then be weighted using a weighting factor 33 specified by the data source, whereby each data source can have its own weighting factor, with which the point values are scaled. For example, point values from the vehicle data source 15 and the user data source 18 may have a higher weight and be weighted with a weighting factor 33 of 35 percent and 40 percent, respectively.

In a step S18, the respective weighted point values of the respective vehicle components can then be combined to form a ranking value, with the respective weighted point values of each vehicle component preferably being summed up.

In a step S20, a selection list of the vehicle components can then be provided for the motor vehicle, with the vehicle components on the selection list being sorted depending on the respective rank value. The appropriate vehicle component can then be selected from this selection list in a step S22 and the component improvement measure can be initiated. This means, for example, that the selected vehicle component is made available in a workshop and a modification date is reserved. The selected vehicle component can then be installed in the motor vehicle on the conversion date.

It is preferably provided that the weighting factors 33 of the respective data sources can be changed by a machine learning algorithm. Here, the machine learning algorithm can check into which position of the selection list the finally selected vehicle component was sorted by the weighting factor 33 in step S20, whereby the weighting factors responsible for the positioning can be adjusted depending on the position of the selected vehicle component. For example, a vehicle component that was previously sorted to a low position but was still selected by a user may help adjust the weighting factors 33 of the data sources responsible for the positioning. In particular, the machine learning algorithm can learn which data sources are of particular importance to a user and increase the weighting factors 33 of these data sources.

In 2 a schematic motor vehicle 34 with a computing device 36 is shown according to an exemplary embodiment. The computing device 36 can, for example, be an infotainment system of the motor vehicle 34, wherein the computing device 36 can be designed to carry out the method for initiating the component improvement measure of the vehicle component. Alternatively, the computing device 36 can be a mobile terminal of a user of the motor vehicle 34, which is designed to carry out the method. For example, the computing device 36, which is designed as a mobile terminal, can couple to the motor vehicle 34 via a mobile data connection in order, for example, to determine current vehicle equipment and a compatibility parameter. Preferably, a system can also be provided with the motor vehicle 34, the computing device 36 and a vehicle-external storage device for retrieving the vehicle component selection, wherein the system can, for example, comprise a server to which computing steps of the method can be outsourced, wherein the system can be designed to do so to carry out procedures.

In another exemplary embodiment, one aspect is that a user request first goes through a compatibility check, where two options may be available. Either the user has access to their vehicle identification number (VIN number). In this case, an algorithm compares the vehicle identification number with a manufacturer database to retrieve comprehensive vehicle information such as model, year, engine type, tire size, and so on. If the vehicle identification number were not available, provision could be made for the user to manually enter their vehicle data into the system.

Once the exact vehicle model is identified, the algorithm may be able to create a comprehensive list of compatible vehicle components. The next step may involve data processing. The algorithm looks at data from various data sources and analyzes this data to find relevant product answers for that specific user query. The data set can be divided into two clusters, static data and dynamic data.

For example, static data can be the user location based on the IP address of the smartphone or computer. From this point on, the algorithm can, for example, perform a country check to determine whether or not the customer is in a country with no speed limit. If this is the case, then a recommended vehicle component would be, for example, the removal of a top speed limiter. The algorithm can also analyze a timestamp in correlation with the user's location to find a relevant product during that period of the year, for example winter sports tires for a query between 01.11. and 01.03.

With dynamic data, the algorithm can access detailed vehicle data such as fuel consumption or driving behavior via a vehicle diagnostic connection (OBD2 connection) on the vehicle. For example, aggressive acceleration behavior may be detected, which may result in a recommendation for a power and torque tuning product.

Dynamic data can also come from platform sales data, providing information about what people who own the same vehicle or configuration often buy. Additionally, weather data can also be used to determine suitable products for specific weather conditions.

Once a list of compatible relevant vehicle components has been created, the algorithm can calculate a weighted order of vehicle components to prioritize these recommended vehicle components and advance the vehicle component most relevant to the user. For example, dynamic sales data and vehicle data may be valued higher than other data sources because these data are the most accurate in relation to the user's profile and can lead to increased relevance in terms of recommendations. For example, static location data and weather dynamic data that are of short-term relevance can be evaluated below.

This weighted calculation allows the algorithm to create a final ranking list in descending order of the most relevant vehicle components.

The examples show how the invention can provide a suggestion algorithm for vehicle components.

Claims (9)

Method for initiating a component improvement measure of a vehicle component of a motor vehicle (34), comprising the steps: a) sending (S10) a request to initiate the component improvement measure; b) determining (S12) a current vehicle equipment (11) and a compatibility parameter (10) of the motor vehicle by a computing device (36) according to the sent request, the compatibility parameter (10) determining which vehicle components are compatible with the motor vehicle; c) retrieving (S14) a vehicle component selection from at least one vehicle-external storage device by the computing device (36), the vehicle component selection being filtered from all vehicle components of the vehicle-external storage device at least depending on the current vehicle equipment (11) and the compatibility parameter (10); d) Carrying out (S16) a weighting process by the computing device (36), whereby predetermined data sources (13, 14) are analyzed to carry out the weighting process to determine suitable vehicle components, the analysis resulting in a separate data profile for each of the data sources (13, 14). (16, 19, 22, 28, 30) is determined, with the respective vehicle components of the vehicle component selection being assigned a respective point value (17, 20, 23, 29, 31) depending on the respective data profile (16, 19, 22, 28, 30). is assigned, with each point value (17, 20, 23, 29, 31) also being assigned through the data the weighting factor (33) specified by the source is weighted, the weighting factor (33) indicating how important the data source (13, 14) is for assessing the need for the vehicle component; e) combining (S18) the respective weighted point values of the respective vehicle component into a ranking value of the respective vehicle component by the computing device (36); f) providing (S20) a selection list of the vehicle components for the motor vehicle by the computing device (36), the vehicle components on the selection list being sorted depending on the respective rank value; g) selecting (S22) a vehicle component from the selection list and initiating the component improvement measure, an exchange or installation of the selected vehicle component being carried out as a component improvement measure; wherein the data sources comprise at least one vehicle data source (15), vehicle sensor data of the motor vehicle being measured for the vehicle data source, a driving profile (16) of the motor vehicle (34) being determined from the vehicle sensor data and the point values (17) of the vehicle data source (15) being determined in Dependency of the driving profile (16) can be assigned. Procedure according to Claim 1 , wherein the determination of the current vehicle equipment (11) and the compatibility parameter (10) is carried out by means of a data retrieval depending on a vehicle identification number. Method according to one of the preceding claims, wherein for the determination in step b) the current vehicle equipment (11) is recognized and provided by a control unit of the motor vehicle. Method according to one of the preceding claims, wherein static (13) and dynamic (14) data sources are analyzed to carry out the weighting process. Method according to one of the preceding claims, wherein the data sources comprise at least one user data source (18), wherein a selection behavior of users of the method is measured for the user data source, wherein a swarm profile (19) is determined from the selection behavior of the users and wherein the point values (20) of the user data source (18) are assigned depending on the swarm profile (19). Method according to one of the preceding claims, wherein the data sources include at least one weather data source (21) and/or metadata (25) of the sent request, weather data being measured for the weather data source (21), a weather forecast profile (22) being created from the weather data , wherein location information (26) and/or time information (27) is determined from the metadata (25), the point values (23, 29, 31) depending on the weather forecast profile (22) and/or from the metadata (25). determined location (26) and/or time information (27) can be assigned. Method according to one of the preceding claims, wherein the weighting factor (33) of the respective data source (15, 18, 21, 24, 25, 32) is determined by means of a machine learning algorithm, the machine learning algorithm checking to which position of the selection list the The vehicle component selected in step g) was sorted by the weighting factor (33) of the respective data source, the weighting factors responsible for the positioning being adjusted depending on the position of the selected vehicle component. Computing device (36) which is designed to carry out the method according to one of the preceding claims. Motor vehicle (34) with a computing device (36). Claim 8 .

Images