Method for operating system and product thereof

Abstract

The present disclosure relates to a method for operating a system, comprising: obtaining, by the system, user data relating to at least one user of the system from at least one source; analyzing, by the system, the user data to determine at least one user attribute of a user of the system; the at least one user attribute is analyzed by the system. The method further includes controlling, by the system, at least one particular element of the system in a first manner based at least in part on at least one result of the analysis of the at least one user attribute.

Description

Technical Field

[0001] The present disclosure relates to a method for operating a system, such as a vehicle system of a vehicle. Further embodiments relate to a computer program product, a control unit for a system, and a vehicle. Background Art

[0002] Nowadays, it's increasingly necessary for users to interact with technical systems, for example via human-machine interfaces. This is particularly true in the automotive sector, where users interact intensively with vehicle systems. However, many users are uncomfortable operating impersonal systems. Consequently, they may not utilize the full functionality provided by the respective systems. Furthermore, users may become less willing to accept information provided by the systems, or in some cases, even deactivate the systems or parts of them. This can lead to overall lower user engagement, satisfaction, and immersion.

[0003] Therefore, it is necessary to improve the design or configuration of the corresponding system. Summary of the Invention

[0004] According to one aspect of the present disclosure, a method for operating a system including a vehicle system associated with a vehicle is provided. The method includes:

[0005] - obtaining, by the system from at least one source, user data relating to at least one user of the system;

[0006] - analyzing the user data by the system to determine at least one user attribute of a user of the system;

[0007] - analyzing the at least one user attribute by the system; and

[0008] - controlling, by the system, at least one particular element of the system in a first manner based at least in part on at least one result of the analysis of the at least one user attribute.

[0009] Controlling specific elements as described can enhance user engagement and immersion in the system. Specifically, the in-vehicle environment can be dynamically adapted, for example, personalized, based at least on at least one result of analyzing at least one user attribute. This is because specific elements can ultimately be adapted based on the user's attributes.

[0010] A two-stage approach is applied, in which the user data is analyzed and, based on the results of this analysis (ie, the user attributes), results are obtained that serve as the basis for controlling the system. The two-stage approach has the particular advantage that fine-grained information can be retrieved from the user data.

[0011] While the content disclosed in the present application is particularly concerned with vehicles, and thus the system is designed as a vehicle system associated with a vehicle, its applicability is also valuable outside of vehicles (particularly the in-vehicle environment of vehicles) (e.g. public displays and self-service terminals). Thus, the system can be part of a public display and / or a self-service terminal.

[0012] Obtaining user data can comprise sensing an environment of the system by a sensor system (such as a camera device). As a result of the sensing, user data related to a user of the system can be obtained. In particular, at least one image of the user of the system can be obtained. The environment of the system can be an in-vehicle environment of a vehicle using the system. Alternatively or in addition, obtaining user data can comprise accessing, by the system, at least one image of the user which can be stored outside of the system, such as at least one image of the user stored on a social media platform.

[0013] Such a sensor system is a preferred source for obtaining information about the user. Preferably, the sensor system is part of the system (or the vehicle associated with the vehicle system).

[0014] Analyzing the user data can comprise determining, by the system, information related to an appearance of the user based at least in part on the user data. For example, the information can be information related to at least one of: at least one upper body garment, at least one lower body garment, at least one hat with a brim, at least one hat without a brim, at least one pair of glasses, at least one pair of shoes, and / or at least one accessory worn by the user, respectively. The determined information can be used as at least one user attribute.

[0015] For example, the user data can contain information about the category of clothing and accessories worn by the user. This can be one of the stages in the analysis method provided herein.

[0016] A CNN multi-label classifier can be used for analyzing the user data and / or for determining the information related to the appearance of the user. Alternatively or in addition, at least one external fashion dataset can be used for determining the information related to the appearance of the user.

[0017] A CNN is a convolutional neural network. Such a CNN can be pre-trained on labeled user data which has been collected and / or synthetically generated at an earlier time.

[0018] Analyzing the at least one user attribute can comprise determining, by the system, information related to an attribute of the user based at least in part on the user attribute. For example, the information can be information related to at least one of: at least one color, at least one design, at least one pattern, at least one material, at least one brand, and / or at least one appearance classification (such as formal, casual, avantgarde, and / or professional) of the user attribute, respectively.

[0019] The CNN multi-label classifier may be used to analyze at least one user attribute and / or determine information related to the user attribute.

[0020] Such a CNN can be pre-trained on annotated user attributes that have been collected and / or synthetically generated earlier.

[0021] Controlling the specific element of the system in the first manner may comprise adapting, by the system, a secondary characteristic or a secondary appearance of the specific element or a portion thereof, such as at least one color of the specific element or a portion thereof.

[0022] For example, the secondary characteristics or appearance of a particular element may take into account the user's current preferences. Thus, the secondary characteristics or appearance of a particular element may be adapted in real time based on the user's contextual attributes, behavior, and / or emotions. The type of device (e.g., vehicle, external display, etc.) may also be taken into account.

[0023] For example, the specific element may be a human-machine interface (such as a touch-sensitive monitor), and the secondary characteristic or appearance of the human-machine interface may refer to the color of the human-machine interface (eg, the primary color used by the monitor display).

[0024] For example, the specific element may be an ambient light unit and the secondary characteristic or appearance of the ambient light unit may refer to the color of the light emitted by the ambient light unit.

[0025] In this way, adaptation of specific elements can provide a sense of personalization and ownership, therefore, providing better user engagement and experience.

[0026] The method may further comprise:

[0027] - The system stores the continuous analysis results of user attributes in the database, thereby forming a database with historical analysis results;

[0028] - evaluating, by the system, one or more historical analysis results stored in a database; and

[0029] - controlling, by the system, a particular element of the system in a second manner based at least in part on at least one result of the evaluation of the historical analysis results.

[0030] Evaluating the historical analysis results can provide general information about the user, thereby making it possible to adapt the system in an overall way to meet the user's general requirements in a comfortable manner.

[0031] Controlling a specific element of the system in a second manner may include: adapting the main characteristics or main appearance of the specific element or a part thereof by the system, such as adapting the number of displayed sub-elements, at least one layout, at least one icon style, at least one shape and / or at least one typesetting of the specific element or a part thereof, respectively.

[0032] For example, the above-mentioned main characteristics or appearance of a specific element can take into account the user's long-term preferences. Therefore, the above-mentioned main characteristics or appearance of a specific element can be the characteristics or appearance of a specific element that are intermittently adapted based on the user's (especially general) style and / or personality.

[0033] For example, a specific element may be a human-machine interface (e.g., a touch-sensitive monitor), and the primary characteristics or appearance of the human-machine interface may refer to one or more of the number, layout, icon style, shape, and typesetting of the displayed sub-elements of the human-machine interface. The human-machine interface may include one or more displays, controls, input devices, and / or output devices (e.g., visual, tactile, or auditory). The number of displayed sub-elements is an example of a visual adaptation; for example, the adaptation may also be auditory and / or tactile.

[0034] In this way, adaptation of specific elements can provide a sense of personalization and ownership, therefore, providing better user engagement and experience.

[0035] The method may further comprise:

[0036] - receiving, via the system, contextual information related to the context of current use of the system and / or the context of current user actions. Such contextual information may be calendar information of at least one user, a route destination of at least one user, at least one current location of a vehicle, at least one map, at least one traffic density, and / or at least one road type;

[0037] - determining, by the system, based at least in part on the context information, a first time to begin controlling the particular element in the first manner and / or a second time to begin controlling the particular element in the second manner; and

[0038] - starting, by the system, controlling the specific element in the first manner and / or the second manner at the determined first time and / or second time.

[0039] This allows for determining optimal scenarios for adapting specific elements. For example, if a user is planning to visit a special event and / or location (e.g., a racetrack and / or beach), the system (in the case of a vehicle system) can adapt specific elements in time for the event to put the user in the appropriate mood. It can also be advantageous to check whether the mood has changed.

[0040] The method may further include: receiving, by the system, feedback from the user regarding at least one result of controlling the specific element in the first manner and / or the second manner. For example, the feedback may be an acceptance and / or rejection of the at least one result of controlling the specific element. The user may provide the feedback via some input device of the system. The method may then include: controlling, by the system, the specific element in the first manner and / or the second manner based on at least one evaluation of the received feedback.

[0041] In this way, an even more appropriate adaptation to the specific element may be provided.

[0042] The method may further include controlling, by the system, the specific element in the first manner and / or the second manner further based on at least one evaluation of at least one of the visual attention score, the visual similarity score, and the content readability score.

[0043] The visual attention score may be obtained based on eye tracking data and / or driving behavior data, and / or it may include information about total glance duration, time on task, attention, lane keeping behavior, steering behavior, and / or steering wheel reversal rate.

[0044] For example, to calculate visual attention scores between an original user interface (UI) theme and an adapted UI theme, eye-tracking metrics and predictive gaze attention models can be used. First, key elements in the UI (such as navigation bars, search bars, and primary buttons) are identified and defined as areas of interest (AOIs). Then, eye-tracking studies are conducted with participants using both UIs, capturing metrics such as fixation duration and counts, which indicate how long and how often users look at specific elements. Alternatively, predictive gaze attention models such as the Saliency model or DeepGaze can be used, which simulate and predict where users are likely to focus their attention. The UI designs are fed into these models to generate heatmaps and attention scores. Visual attention scores are compared by analyzing gaze distribution, heatmap intensity, and overall engagement levels. Static tests such as t-tests or ANOVAs can help identify significant differences in visual attention between the two UIs. This process can reveal how effectively each UI captures user attention and guide further design improvements.

[0045] A visual similarity score is obtained by comparing the standard HMI to the adapted HMI version pixel by pixel and using existing tools to calculate scores based on color and form.

[0046] For example, to compute the visual similarity score between two user interface (UI) versions (e.g., the original theme and the adapted theme), computer vision techniques facilitated by tools such as OpenCV and scikit-image can be employed. These tools help extract key visual features from the two UI designs, such as color histograms, texture patterns, and structural layouts. The extracted features are then represented as feature vectors, which are then analyzed for similarity using metrics implemented via libraries such as numpy and scpy (e.g., cosine similarity or Euclidean distance). Normalization of the feature vectors ensures unbiased comparisons across different scales. By quantifying the similarity between feature vectors, insights into the visual coherence and consistency of the UI adaptation can be gained, guiding iterative refinement to optimize the user experience and aesthetic consistency across interfaces.

[0047] The content readability score may be derived based on eye tracking data and / or driver monitoring data, and / or it may include information about single glance duration, total glance duration, use of imitation, and / or fault conditions.

[0048] For example, to calculate a content readability score, you can focus on analyzing text readability using established readability guidelines and contrast ratios. The Web Content Accessibility Guidelines (WCAG) outline several key principles for enhancing accessibility, such as perceivable, actionable, understandable, and robust content. Ensure that the contrast between text color and background color meets WCAG guidelines. Additionally, WCAG recommends using adequate font size and legible fonts. Automated readability tools like Readable can also simplify this process, providing scores and suggestions for improvements.

[0049] The specific element may include at least one ambient light unit and / or at least one human-machine interface. The at least one human-machine interface may have one or more parts, such as at least one touch-sensitive sensor, at least one key, and / or at least one knob. For example, controlling the specific element (e.g., the human-machine interface) in a first manner and / or a second manner may cause one or more of its parts (e.g., the sensor, key, and / or knob) to be adapted, such that primary and / or secondary characteristics or appearance of the specific element or its parts are adapted.

[0050] A particular element may include at least one output function. The output function may be configurable or configured to provide a perceptible output, such as a visual, acoustic, and / or tactile output, to a user of the system (eg, a driver of a vehicle).

[0051] Controlling of the specific element may be performed in the form of output functions such that an output is provided to at least one user via at least one output function.

[0052] The system can be a vehicle system associated with a vehicle. In this case, the user of the vehicle system can be the driver of the vehicle.

[0053] The specific element can be provided in an interior of the vehicle. The specific element is accessible to the user during driving of the vehicle.

[0054] According to another aspect of the present disclosure, a computer program product is provided. The computer program product comprises portions of program code which, when executed by a processor of a control unit of a system, in particular a vehicle system associated with a vehicle, cause the control unit to perform a method as provided herein.

[0055] According to another aspect of the present disclosure, a control unit for a system, in particular a vehicle system associated with a vehicle, is provided. The control unit comprises a processor and a storage device operably coupled to the processor. The storage device stores portions of program code which, when executed by the processor, cause the control unit to perform a method as provided herein.

[0056] According to another aspect of the present disclosure, a vehicle is provided. The vehicle comprises a vehicle system comprising a control unit as provided herein and one or more specific elements, such as a human-machine interface and / or an ambient light unit, operably coupled to the control unit. BRIEF DESCRIPTION OF DRAWINGS

[0057] Further details and advantages of the embodiments will become clear upon consideration of the following detailed description taken in conjunction with the accompanying drawings, in which:

[0058] Figure 1 is a method for operating a vehicle system of a vehicle according to an embodiment;

[0059] Figure 2 is a vehicle having a vehicle system comprising a control unit according to an embodiment;

[0060] Figure 3 is a control unit for a vehicle system according to an embodiment. DETAILED DESCRIPTION

[0061] Figure 1 A flowchart of a method 100 for operating a system, here a vehicle system associated with a vehicle, is shown. In some examples, the method 100 is performed by a control unit of the vehicle system.

[0062] The method 100 comprises a step 110 of obtaining, by the system, user data related to at least one user of the system from at least one source.

[0063] The method 100 further includes step 120 : analyzing the user data by the system to determine at least one user attribute of a user of the system.

[0064] The method 100 further includes step 130 : analyzing the at least one user attribute by the system.

[0065] The method 100 further includes step 140 of controlling, by the system, at least one specific element of the system in a first manner based at least in part on at least one result of the analysis of the at least one user attribute.

[0066] For example, a specific element of the system may be a human machine interface or an ambient light unit. The specific element may be arranged in the interior of the vehicle.

[0067] Figure 2 A vehicle 200 is shown schematically and exemplarily. The vehicle 200 includes a vehicle system 210. The vehicle system 210 includes a control unit 220, which includes a processor 222 and a data storage device 224 operatively connected to the processor 222. The vehicle system 210 also includes a sensor system 240. Figure 2 2 is exemplarily shown as including a camera device 240 for taking a photo of a user of system 210, here the user is driver D of vehicle 200. Vehicle system 210 also includes at least one specific element 230, here a human-machine interface with a touch-sensitive monitor. The human-machine interface is configured to provide a perceptible output to driver D, such as a visual and / or acoustic output. For example, this can be achieved by control unit 220 generating a corresponding control signal and outputting the control signal to specific element 230. Notably, in some examples, the output includes any of visual, acoustic, olfactory, and / or tactile output. In some examples, the visual output is provided via a display unit in specific element 230 of vehicle system 210. In addition, in some examples, the acoustic output is provided via one or more speakers in specific element 230 of vehicle system 210. In some examples, the olfactory output is provided via one or more fragrance dispensers in specific element 230 of vehicle system 210. Additionally, in some examples, tactile output is provided via force feedback functionality included in a steering device, one or more pedals, and / or a vibration device in a seat of vehicle system 210 .

[0068] In the example shown, the vehicle system 210 further includes a communication unit 250 adapted to receive and transmit communication signals, such as radio signals, via a communication network to which the vehicle system 210 is wirelessly connected. Each of the specific elements of the output 230, the sensor 240, and the communication unit 250 is operable to be operatively connected to the control unit 220.

[0069] Control unit 220 may be configured to obtain user data related to at least one user of system 210 (e.g., from driver D) from at least one source. Control unit 220 may also be configured to analyze the user data. By analyzing the user data, control unit 220 may be operable to determine at least one user attribute of the user of system 210. Alternatively, at least one result of the analysis may be at least one user attribute of the user of system 210. This analysis may be considered the first stage of a multi-stage data processing approach.

[0070] For analyzing the user data, the control unit 220 may use any type of user data that is available to the vehicle system 210 and that may indicate at least one user attribute of a user of the system 210. For example, the sensor 240 may be operable to detect one or more user data that may indicate one or more user attributes of a user of the system 210 in real time.

[0071] The control unit 220 may be configured to analyze the at least one user attribute. This analysis may be considered the second stage of a multi-stage data processing scheme. Of course, at least one result of this analysis may be used for further action later.

[0072] Control unit 220 may be configured to control at least one specific element of system 210 in a first manner based, at least in part, on at least one result of the analysis of the at least one user attribute. Because a multi-stage data processing approach is employed, control of a specific element is based on the results of the second-stage analysis, thereby extracting features to be considered for control at several stages. This enables more fine-grained control of the corresponding element.

[0073] In some examples, control unit 220 can be configured to analyze user data using a trained machine learning model (e.g., a CNN). Data available to vehicle system 210 (e.g., user data) can be provided as input to the trained machine learning model. In some examples, the trained machine learning model is stored via storage device 224. In other examples, the trained machine learning model is at least partially stored at a network node external to vehicle 200, to which control unit 220 is communicatively connected via communication unit 250.

[0074] In some examples, the control unit 220 can be configured to analyze the at least one user attribute by using a trained machine learning model, such as a CNN. Data available to the vehicle system 210, such as the at least one user attribute, can be provided as input to the trained machine learning model. In some examples, the trained machine learning model is stored by the storage device 224. In other examples, the trained machine learning model is stored at least partly at a network node external to the vehicle 200, to which the control unit 220 is communicatively connected by the communication unit 250.

[0075] In some examples, for obtaining the user data, the control unit 220 can be configured to sense an environment of the system. For this purpose, the sensor system 240 can be used. The sensor system 240 can be implemented in the form of a camera device. The camera device can be part of the system. In particular in the case of a vehicle system, for this purpose, a camera already present in the vehicle can be employed. In any case, the sensor system 240 allows obtaining user data related to a user of the system. For example, with the camera device, at least one image of a user of the system 210 can be obtained. It is noted that the acquisition, storage and use of personal information / user personal data involved in the technical solutions of the present disclosure comply with the relevant legal regulations and do not violate public order and good customs.

[0076] In some examples, for obtaining the user data, the control unit 220 can be configured to access at least one image of the user stored external to the system 210. For example, the externally stored image can be retrieved via the communication unit 250. The externally stored image can be at least one image of the user stored on a social media platform.

[0077] In some examples, for analyzing the user data, the control unit 220 can be configured to determine information related to an appearance of the user based at least partly on the user data. The determined information can then be used as the at least one user attribute. For example, the appearance of the user can be determined based on information related to at least one upper body garment, at least one lower body garment, at least one hat with brim, at least one hat without brim, at least one pair of glasses, at least one pair of shoes and / or at least one accessory worn by the user, respectively.

[0078] In addition, a CNN multi-label classifier can be used to analyze user data and / or to determine information related to the user's appearance. The CNN multi-label classifier can be a trained machine learning model. In some examples, the trained machine learning model is stored via storage device 224. In other examples, the trained machine learning model is at least partially stored at a network node external to vehicle 200, to which control unit 220 is communicatively connected via communication unit 250. Alternatively or in addition, at least one external style dataset can be used to determine information related to the user's appearance. For example, the dataset can be retrieved via communication unit 250.

[0079] In some examples, for analyzing the at least one user attribute, the control unit 220 can be configured to determine information related to the user attribute based at least in part on the user attribute. The information related to the at least one user attribute can respectively indicate at least one color, at least one design, at least one pattern, at least one material, at least one brand, and / or at least one appearance classification of the user attribute, such as formal, casual, fashion, and / or professional.

[0080] In addition, the CNN multi-label classifier can be used to analyze at least one user attribute and / or to determine information related to the user's attribute. The CNN multi-label classifier can be a trained machine learning model. In some examples, the trained machine learning model is stored by storage device 224. In other examples, the trained machine learning model is at least partially stored at a network node external to vehicle 200, and control unit 220 is communicatively connected to the network node via communication unit 250.

[0081] In some examples, for controlling a specific element of the system in the first manner, the control unit 220 may be configured to adapt a secondary characteristic or appearance of the specific element or portion thereof. For example, the secondary characteristic or appearance may be at least one color of the specific element or portion thereof.

[0082] In some examples, control unit 220 may be further configured to store the results of the continuous analysis of the user attributes in a database, thereby forming a database with historical analysis results. Control unit 220 may also be configured to evaluate one or more historical analysis results stored in the database and control a specific element of the system in a second manner based at least in part on at least one result of the evaluation of the historical analysis results.

[0083] In some examples, control unit 220 can be configured to evaluate historical analysis results using a trained machine learning model (e.g., a CNN). Data available to vehicle system 210 (e.g., historical data) can be provided as input to the trained machine learning model. In some examples, the trained machine learning model is stored via storage device 224. In other embodiments, the trained machine learning model is at least partially stored at a network node external to vehicle 200, to which control unit 220 is communicatively connected via communication unit 250.

[0084] According to some of the foregoing examples, in some examples, the user data includes at least one real-time sensor data that has been obtained by the sensor system 240 of the vehicle system 210. Additionally or alternatively, in some examples, the user data includes communication data that has been received by the communication unit 250. Additionally or alternatively, in some examples, the control unit 220 uses historical data, such as stored sensor data, to control a particular element, where the data has been stored by the storage device 224.

[0085] In some examples, for a specific element of the system controlled in the second manner, the control unit 220 may be configured to adapt a primary characteristic or appearance of the specific element or portion thereof. For example, the primary characteristic or appearance may be the number of displayed sub-elements, at least one layout, at least one icon style, at least one shape, and / or at least one typesetting of the specific element or portion thereof, respectively.

[0086] In some examples, the control unit 220 may also be configured to receive contextual information related to the context in which the system is currently being used. Alternatively or in addition, the contextual information may also be related to the context of the user's current actions. Examples of such information are schedule information for at least one user, a route destination for at least one user, at least one current location of a vehicle, and / or at least one map. The control unit 220 may then also be configured to determine, based at least in part on the contextual information, a first time to begin controlling a specific element in a first manner. Additionally or alternatively, a second time to begin controlling the specific element in a second manner may also be determined. In any case, the control unit 220 may then also be configured to begin controlling the specific element in the first manner and / or the second manner at the determined first time and / or second time.

[0087] In some examples, the control unit 220 can be further configured to receive feedback from a user regarding controlling the particular element in the first manner and / or the second manner. For example, the user can provide feedback by accepting and / or rejecting the form of controlling the particular element. The control unit 220 can then be further configured to control the particular element in the first manner and / or the second manner further based on at least one evaluation of the received feedback.

[0088] In some examples, the control unit 220 can be further configured to control the particular element in the first manner and / or the second manner further based on at least one evaluation of at least one of the visual attention score, the visual similarity score, and the content readability score.

[0089] According to some of the preceding examples, the particular element comprises at least one ambient light unit and / or at least one human-machine interface. For example, the human-machine interface can have at least one touch-sensitive monitor, at least one key, and / or at least one knob.

[0090] Further, in some examples, the particular element can comprise at least one output function. The output function can be configurable or configured to provide a perceptible output, such as a visual, acoustic, and / or haptic output, to a user of the system, such as a driver of a vehicle.

[0091] Figure 3 A control unit 300 of a system is schematically and exemplarily illustrated, where the system is a vehicle system associated with a vehicle. The control unit 300 comprises a processor 310 operably connected to a storage device 320. The control unit 300 can be configured to receive and / or output data signals via one or more interfaces 312, 314, such as Figure 3 schematically illustrated in

[0092] The storage device 320 stores program code executable by the processor 310. The control unit 300 can be implemented in the same way as the control unit 220 of the vehicle system 210 in Figure 2 In other examples, the control unit 300 can be at least partially implemented at one or more network nodes in network communication with the vehicle system, to receive data from the vehicle system and / or output and transmit generated data to the vehicle system via a communication network.

[0093] The storage device 320 stores portions of program code that, when executed by the processor 310, configure the control unit 300 to perform operations according to any of the examples described above in connection with Figure 1 and 2 The control unit 300 can be implemented in the same way as the control unit 220 of the vehicle system 210 in

[0094] The storage device 320 stores program codes, which, by interacting with the processor 310 , constitute a user data acquisition module 322 , which is configured to obtain user data related to at least one user of the system from at least one source.

[0095] The storage device 320 also stores program code that constitutes a user data analysis module 324, which is used to analyze user data to determine at least one user attribute of a user of the system.

[0096] The storage device 320 further stores program codes constituting a user attribute analysis module 326 , which is configured to analyze the at least one user attribute.

[0097] The storage device 320 also stores program code constituting a specific element control module 328 for controlling at least one specific element of the system in a first manner based at least in part on at least one result of analyzing the at least one user attribute.

Claims

1. A method for operating a system, characterized in that The method comprises: - obtaining, by the system from at least one source, user data relating to at least one user of the system; - analyzing the user data by the system to determine at least one user attribute of the user of the system; - analyzing said at least one user attribute by said system; - controlling, by the system, at least one particular element of the system in a first manner based at least in part on at least one result of analyzing the at least one user attribute; Wherein, the system includes a vehicle system associated with a vehicle.

2. The method according to claim 1, characterized in that Obtaining user data includes: - sensing the environment of the system by a sensor system, thereby obtaining the user data related to the user of the system; and / or - accessing, by the system, at least one image of the user stored externally to the system.

3. The method according to claim 1 or 2, characterized in that Analyzing the user data includes: - determining, by the system, information related to the user's appearance based at least in part on the user data, and using the determined information as the at least one user attribute, The CNN multi-label classifier is used to analyze the user data and / or to determine information related to the user's appearance, and / or at least one external style dataset is used to determine information related to the user's appearance.

4. The method according to any one of claims 1 to 3, characterized in that Analyzing the at least one user attribute includes: - determining, by the system, information related to attributes of the user based at least in part on the attributes of the user, The CNN multi-label classifier is used to analyze the at least one user attribute and / or to determine information related to the attribute of the user.

5. The method according to any one of claims 1 to 4, characterized in that Controlling the specific element of the system in the first manner comprises adapting, by the system, secondary characteristics of the specific element or a portion of the specific element, wherein the secondary characteristics of the specific element or a portion of the specific element comprise at least one color of the specific element or a portion of the specific element.

6. The method according to any one of claims 1 to 5, characterized in that The method comprises: - Storing the continuous analysis results of user attributes in a database through the system, thereby forming a database with historical analysis results; - evaluating, by said system, one or more of said historical analysis results stored in said database; - controlling, by the system, the particular element of the system in a second manner based at least in part on at least one result of the evaluation of the historical analysis results.

7. The method according to claim 6, characterized in that Controlling the specific element of the system in the second manner includes: adapting the main characteristics of the specific element or the part of the specific element through the system, and the main characteristics of the specific element or the part of the specific element include at least one of the following: the number of displayed sub-elements of the specific element or the part of the specific element, at least one layout, at least one icon style, at least one shape and / or at least one typesetting.

8. The method according to any one of claims 1 to 7, characterized in that The method comprises: - receiving, by the system, context information related to a context of current use of the system and / or a context of a current action of the user, the context information comprising: schedule information of at least one user, a route destination of at least one user, at least one current position of the vehicle, at least one map, at least one traffic density and / or at least one road type; - determining, by the system, a first time to start controlling the specific element in the first manner and / or a second time to start controlling the specific element in the second manner based at least in part on the context information; - starting, by the system, controlling the specific element in the first manner and / or the second manner at the determined first time and / or second time.

9. The method according to any one of claims 1 to 8, characterized in that The method comprises: - receiving, through the system, feedback from a user regarding at least one result of controlling the specific element in the first manner and / or the second manner, the feedback comprising: acceptance and / or rejection of at least one result of controlling the specific element; - controlling, by the system, the specific element in the first manner and / or the second manner further based on at least one evaluation of the received feedback.

10. The method according to any one of claims 1 to 9, characterized in that The method comprises: - controlling, by the system, the specific element in the first manner and / or the second manner further based on at least one evaluation of at least one of a visual attention score, a visual similarity score, and a content readability score.

11. The method according to any one of claims 1 to 10, characterized in that The specific elements include: at least one ambient light unit and / or at least one human-machine interface, wherein the at least one human-machine interface includes a human-machine interface having at least one touch-sensitive detector, at least one key and / or at least one knob.

12. The method according to any one of claims 1 to 11, characterized in that The specific element includes: at least one output function, wherein the at least one output function is configured to provide a perceptible output to a user of the system, the output including visual, acoustic and / or tactile output.

13. A computer program product, characterized in that The computer program product comprises portions of program code which, when executed by a processor of a control unit of a system, cause the control unit to perform a method according to any one of claims 1 to 12, wherein the system comprises a vehicle system associated with a vehicle.

14. A control unit for a system, characterized in that, The system includes a vehicle system associated with a vehicle, the control unit includes a processor and a storage device operably coupled to the processor, wherein the storage device stores a portion of a program code, which, when executed by the processor, causes the control unit to perform the method according to any one of claims 1 to 12.

15. A vehicle, characterized in that: The vehicle includes a vehicle system, the vehicle system including: - A control unit according to claim 14; - one or more specific elements operatively coupled to the control unit, wherein the one or more specific elements include a human-machine interface and / or an ambient light unit.

Images