Methods for determining virtual license plate styles and vehicles

Abstract

This application discloses a method for determining virtual license plate styles and a vehicle, relating to the field of intelligent cockpit technology. The method includes: identifying the vehicle user's identity; acquiring relationship data of social relationships associated with the identity; analyzing the relationship data based on a preset social relationship model to determine the relationship type and associated scenario information. The preset social relationship model is determined in advance based on the relationship data and according to preset relationship analysis rules, and is used to characterize the degree of association and scenario relevance between the vehicle user and each social relationship object; and determining the license plate style based on the relationship type and associated scenario information, and displaying the license plate in a virtual license plate display frame based on the license plate style. This method can meet the user's needs for personalized and emotional expression, improving the intelligence level of license plate style customization and user experience.

Description

Technical Field

[0001] This application relates to the field of intelligent cockpit technology, and in particular to a method for determining a virtual license plate style and a vehicle. Background Technology

[0002] As the interactive capabilities of in-vehicle digital interfaces improve, users' demand for personalized displays is increasing. They expect virtual license plates to not only fulfill basic identification functions but also reflect personal style or emotional expression in specific contexts. Related technologies typically allow users to personalize virtual license plates by manually inputting or selecting preset styles for rendering and display on the digital interface.

[0003] In related technologies, virtual license plate customization solutions generally rely on static input from individual users. For example, users directly set explicit parameters such as numbers, colors, or patterns, and the system generates virtual license plates with fixed styles accordingly. While this method achieves basic personalization, its data dimension is singular, processing only explicit information actively provided by users. It is difficult to overcome the bottleneck of insufficient personalization, and the generated virtual license plate styles are disconnected from users' real social scenarios, failing to meet users' expectations for deep personalization and emotional expression. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in related technologies. To this end, the first objective of this application is to propose a method for determining virtual license plate styles. This method acquires relationship data of associated social relationships, determines the relationship type and associated scenario information based on this data, and then determines the license plate style. This dynamically drives the generation of the license plate style using the user's social relationship data, logically linking the customized style with the user's social scenario. This effectively solves the problem of customized content being detached from the social environment in the prior art, significantly improving the personalization level and scenario adaptability of license plate customization, and enhancing the user's interactive experience. Simultaneously, since the license plate style is generated based on objective relationship data rather than manual selection by the user, the user's operational burden is reduced, achieving an intelligent and automated license plate customization process.

[0005] The second objective of this application is to propose a vehicle.

[0006] To achieve the above objectives, a first aspect of this application proposes a method for determining a virtual license plate style, applied to an intelligent cockpit system. The intelligent cockpit system displays a virtual vehicle model on its digital interface, and the virtual vehicle model is equipped with a virtual license plate display frame. The method includes: identifying the vehicle user's identity; acquiring relationship data of social relationships associated with the identity; analyzing the relationship data based on a preset social relationship model to determine the relationship type and associated scenario information, wherein the preset social relationship model is predetermined based on the relationship data according to preset relationship analysis rules, and is used to characterize the degree of association and scenario association between the vehicle user and each social relationship object; and determining the license plate style based on the relationship type and the associated scenario information, so as to display the license plate in the license plate display frame based on the license plate style.

[0007] According to the virtual license plate style determination method of this application embodiment, the user's identity is identified, and relationship data of social relationships associated with the identity is obtained. The relationship data is analyzed based on a preset social relationship model to determine the relationship type and associated scenario information. The preset social relationship model is determined in advance based on the relationship data and according to preset relationship analysis rules, and is used to characterize the degree of association and scenario association between the user and each social relationship object. The license plate style is determined based on the relationship type and associated scenario information, and then displayed in the license plate display frame based on the license plate style. Therefore, this method can automatically generate license plate styles that adapt to the user's social scenarios based on the user's social relationship data, eliminating the need for the user to manually input and filter personalized needs. This reduces the operational cost of customizing license plate styles and ensures that the customized license plate style deeply matches the user's personal social connections, better meeting the user's needs for personalized and emotional expression. It improves the intelligence level and user experience of license plate style customization and solves the problem of license plate style customization being detached from the user's actual social scenarios and lacking personalization.

[0008] According to one embodiment of this application, the relationship data is analyzed based on a preset social relationship model to determine the relationship type, including: determining the relationship intimacy index of the vehicle user based on the preset social relationship model and the relationship data, and determining the relationship type based on the relationship intimacy index, wherein the relationship data includes at least one of the vehicle user's address book data, social application interaction records, vehicle sensor data, and calendar data.

[0009] According to one embodiment of this application, determining the relationship intimacy index of the vehicle user based on the preset social relationship model and the relationship data includes: determining the call frequency, co-existence duration, and interaction records between the vehicle user and each social relationship object based on the relationship data; and calculating the corresponding relationship intimacy index through the preset social relationship model based on at least one of the call frequency, the co-existence duration, and the interaction records.

[0010] According to one embodiment of this application, the relationship data is analyzed based on a preset social relationship model to determine associated scenario information, including: determining the historical co-occurrence travel records and schedule data between the vehicle user and each social relationship object based on the preset social relationship model and the relationship data; and determining the associated scenario information based on the historical co-occurrence travel records and the schedule data.

[0011] According to one embodiment of this application, determining the license plate style based on the relationship type and the associated scene information includes: determining the license plate style based on the relationship type, the associated scene information, and a preset visual element mapping rule library.

[0012] According to one embodiment of this application, the method further includes: when it is determined that the vehicle has entered a privacy protection mode, replacing the license plate style with a preset general style, or hiding the license plate style.

[0013] According to one embodiment of this application, the method further includes: upon receiving an authorization instruction from the vehicle user or detecting that the vehicle has entered a preset geographical area, determining to enter a privacy protection mode, wherein the preset geographical area includes the coverage area of ​​the chauffeur service platform or the vehicle repair service area.

[0014] According to one embodiment of this application, the method further includes: acquiring physiological state data or emotional state data of the vehicle user; and dynamically adjusting the visual style of the license plate based on the physiological state data or emotional state data, wherein the visual style includes at least one of color tone, pattern complexity, or animation speed.

[0015] According to one embodiment of this application, the method further includes: acquiring external environment information, the external environment information including at least one of light intensity, weather conditions, or surrounding vehicle density; and adjusting the display parameters of the license plate style based on the external environment information, the display parameters including at least one of brightness, color saturation, and transparency.

[0016] To achieve the above objectives, a vehicle is provided in the second aspect of this application, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the above-described method for determining the virtual license plate style.

[0017] According to the embodiments of this application, by executing the above-described virtual license plate style determination method, the vehicle can meet the user's needs for personalized and emotional expression, and improve the intelligence level of license plate style customization and user experience.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0019] Figure 1 This is a flowchart of a method for determining a virtual license plate style according to an embodiment of this application.

[0020] Figure 2 This is a flowchart illustrating a method for determining a virtual license plate style according to a specific example of this application.

[0021] Figure 3 This is a block diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0022] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0023] To achieve personalized customization of virtual license plate styles, the common approach is to pre-store user-configured style parameters, such as background color, font style, border pattern, or custom text. These static parameters are then rendered onto the license plate area on the virtual vehicle model displayed on the in-vehicle screen or mobile terminal. This solution is widely adopted primarily to meet users' basic personalized needs for vehicle appearance display, providing basic customization capabilities that differ from the default style.

[0024] However, this solution performs poorly when applied to intelligent cockpit experiences that require a deep reflection of users' social attributes and dynamic scenarios. In other words, while it provides users with the freedom to manually configure their systems, its reliance on isolated, static input from individual users prevents it from automatically sensing and utilizing the user's complex social network and real-time changing travel scenarios. This results in personalized styles remaining merely superficial, severely lacking emotional connection and intelligent adaptation to the user's real social context. For example, in practical applications, when the vehicle's navigation destination is set to a home address and the occupants include family members, the technology fails to automatically recognize this family-centric social scenario. The rendered license plate style might be identical to that used for solo commuting, failing to create the intended warm family atmosphere. This manifests as low user satisfaction with the customized results and significant shortcomings in the intelligent cockpit system's interactive intelligence and emotional service.

[0025] In-depth analysis reveals that the relevant technologies lack the ability to collect and model user social relationship data. This results in personalized customization relying entirely on manual input from users, severing the logical connection between customized content and users' real-life scenarios. These technologies treat users as isolated individuals, ignoring the fact that users are rooted in multi-dimensional social networks such as family, friends, and colleagues in their real lives. These social relationships and their associated scenarios (such as family trips, friend gatherings, and business receptions) are key factors driving user emotions and determining their social behavior, but the data models of these technologies fail to understand and represent these factors.

[0026] To address the aforementioned issues, this application proposes a method for determining virtual license plate styles. By acquiring multi-source relationship data authorized by the user, the method quantifies and characterizes the user's social relationship network, constructs a computable relationship model, and automatically generates a customized virtual license plate style highly coupled with the current social scenario based on the relationship types and associated scenario information contained in the model. This enables personalized customization to leap from superficial customization based on static user preferences to deep intelligent adaptation based on dynamic user social relationships and scenarios. This solves the technical problems of existing customization methods being disconnected from user social scenarios and lacking sufficient personalization, achieving the effect that the virtual license plate style can intelligently reflect the user's social relationships and travel social attributes.

[0027] In one embodiment of this application, the virtual license plate style determination method is applied to an intelligent cockpit system. A virtual vehicle model is displayed on the digital interface of the intelligent cockpit system, and a virtual license plate display frame is set on the virtual vehicle model. For example, the intelligent cockpit system mainly includes a data acquisition layer, a relationship modeling engine, a customized rule base, a rendering layer, and a vehicle status perception module. The data acquisition layer is responsible for acquiring multi-source relationship data authorized by the user. For example, it connects to the user's address book application through the vehicle communication module, accesses the user's social application interaction records through the social application interface, collects the identity and voice interaction information of in-vehicle occupants through vehicle sensors (such as in-vehicle cameras and microphones), and obtains the user's schedule event data through the calendar application. The relationship modeling engine is a computing unit that receives the above-mentioned multi-source relationship data and aggregates, cleans, and quantitatively analyzes this data through a preset social relationship model. The customized rule base stores a large number of predefined or dynamically generated mapping rules through machine learning. These rules are used to convert the abstract relationship information (such as relationship type and intimacy index) output by the relationship modeling engine into specific visual elements (such as border styles, background patterns, and text content). The rendering layer is responsible for accurately matching and rendering the final generated virtual license plate style onto the license plate area of ​​the virtual vehicle's 3D model displayed on the digital interface (such as an in-vehicle screen or mobile terminal). The vehicle status perception module continuously monitors the vehicle's real-time status, such as current location, navigation destination, and vehicle control permissions. Furthermore, all these modules interact with each other via the vehicle bus or wireless communication network.

[0028] The following description, with reference to the accompanying drawings, describes the method for determining the virtual license plate style and the vehicle proposed in the embodiments of this application.

[0029] Figure 1 This is a flowchart of a method for determining a virtual license plate style according to an embodiment of this application.

[0030] like Figure 1 As shown, the virtual license plate style determination method in this application embodiment may include the following steps: S1 identifies the vehicle user's identity.

[0031] Specifically, the system first identifies the vehicle user. This identification uniquely identifies the current user of the vehicle. This identification can be obtained in various ways. For example, facial recognition via the in-vehicle camera can be compared with a pre-registered user facial feature database in the system to determine the current driver or passenger. Alternatively, the system can pair with the user's mobile device (such as a smartphone or smartwatch) via Bluetooth or near-field communication to read the user's stored account information. Another example is that the user can directly log in to their personal account on the in-vehicle screen by entering their username and password. In some embodiments, if the vehicle-sharing mode involves multiple authorized users, the system can identify them through the press record of the seat memory setting button or the user's specific key fob identification code.

[0032] Therefore, by adopting the above method, the current user can be quickly and accurately identified, avoiding confusion between the personalized license plate settings of different users, and providing accurate identity information for subsequent matching of corresponding license plate styles.

[0033] S2, obtain relationship data of social relationship objects associated with the identity identifier.

[0034] Specifically, after identifying the vehicle user, relationship data of the social relationships associated with that identity can be obtained. This means acquiring the relationship data that the user has pre-authorized to be stored in the system. This relationship data originates from third-party applications previously authorized by the user through mobile devices or the in-vehicle system, and refers to any set of information that can reflect the degree of connection, interaction history, or social network structure between the vehicle user and their social relationships. For example, this may include, but is not limited to, contact fields in an address book, friend lists and chat logs in social applications, time and location data collected by in-vehicle sensors, participant information in a schedule, or combinations thereof, which can be obtained through an API (Application Programming Interface) or local storage after user authorization.

[0035] For example, the system accesses the user's authorized address book through an application programming interface (API) to extract the phone numbers, email addresses, home addresses, and user-defined group information (such as family, friends, and colleagues) of all contacts.

[0036] For example, the system accesses user interaction records in social applications (such as WeChat and Douyin) to extract chat frequency, interaction time, shared group lists, and group tags with each contact. Furthermore, the system obtains data from in-vehicle sensors, such as historical connection records of in-vehicle Bluetooth devices, to identify passengers who frequently travel with the current user, or to identify contacts with high voice interaction frequency through the in-vehicle microphone. In addition, the system obtains the user's calendar data to extract event themes, participant lists, and event types (such as project celebration parties or family weekend trips). This relationship data obtained from different sources collectively constitutes a raw description of the user's social network. It should be noted that all data collection and acquisition are based on the user's explicit informed consent and granted permissions, and are conducted in accordance with legal regulations and relevant privacy protection standards. No personal information of the user will be collected, used, or disclosed without the user's permission. All data is only used in the license plate style determination process, and after use, the data will be anonymized or deleted according to preset privacy management rules to maximize the protection of user information security.

[0037] S3 analyzes relationship data based on a preset social relationship model to determine relationship types and associated scenario information. The preset social relationship model is determined in advance based on relationship data and according to preset relationship analysis rules. It is used to characterize the degree of association and scenario association between vehicle users and various social relationship objects.

[0038] Specifically, after determining the relationship data, it can be analyzed according to a preset social relationship model to determine the relationship type and associated scenario information. The preset social relationship model is pre-determined based on the relationship data and according to preset relationship analysis rules, and is used to characterize the degree of association and scenario relevance between the vehicle user and each social relationship object. That is, this preset social relationship model is the core computing unit of the system, essentially a dynamic computing framework built based on analysis algorithms or machine learning models. During system initialization or the user's first authorization, the system calculates one or more quantitative indicators for each social relationship object based on the user's historical relationship data (such as contacts, social interaction records, travel history, etc.) according to preset relationship analysis rules. These indicators are then associated and stored with the corresponding relationship objects, forming a preset social relationship model specific to that user. Furthermore, this model is not static but dynamically evolves as the user's relationship data is continuously updated. For example, when the user's social application interaction records or shared travel records change, the intimacy index and scenario tags in the model will be adjusted accordingly.

[0039] Relationship type refers to the qualitative classification of the social relationship between the vehicle user and the social relationship object, used to describe the nature or role of the relationship. For example, it may include, but is not limited to, family, close friends, colleagues, business partners, strangers, or derived classifications based on relationship intimacy index or preset labels. Related scenario information refers to contextual data related to the vehicle user's current or historical travel activities, used to characterize the attributes and background of a specific social scenario. For example, it may include, but is not limited to, navigation destination type (such as home address, company, park), the identity combination of passengers in the vehicle, the theme of the scheduled event (such as "airport pickup," "family dinner"), or inferences based on historical shared travel records and schedule data.

[0040] For example, when analyzing relationship data based on a pre-defined social relationship model, the system first compares the currently acquired relationship data (such as current call records and new calendar events) with existing data in the model to verify and update the indicators. Secondly, based on the current state of the model, it quantitatively assesses the degree of association between the vehicle user and each social relationship object, thereby determining the relationship type. For instance, the model might calculate an intimacy index and combine it with contact group tags to classify one contact as a family member and another as a close friend or colleague. Simultaneously, the model also uses the associated scenario tags in the model, combined with currently acquired vehicle status information (such as navigation destination, vehicle occupant identities, and calendar events), to determine associated scenario information matching the current context. For example, if the model records show that the associated scenario tag for a contact's spouse includes "weekend family trip," and the current navigation destination is a forest park, the system can determine the associated scenario information as "weekend family trip." Through these methods, the system can efficiently and accurately extract relationship types and associated scenario information from complex relationship data, thus providing structured input for subsequent pattern generation.

[0041] S4 determines the license plate style based on the relationship type and associated scenario information, and displays the license plate based on the license plate style.

[0042] Specifically, after determining the relationship type and associated scenario information, the license plate style can be determined based on the relationship type and associated scenario information, and then displayed based on the license plate style. For example, the license plate style can be determined through a pre-defined correspondence. For instance, the relationship between the relationship type and associated scenario information and the license plate style can be determined in advance. After the relationship type and associated scenario information are determined, the license plate style can be obtained by directly calling the corresponding relationship.

[0043] For example, if the defined relationship type is "family" and the associated scenario is a weekend family outing, a rule for that relationship might instruct the system to use a warm-style border (such as wood grain or grass texture) and select a recent heartwarming family photo from the family cloud album or the user's device as the background element, process it into a cartoon style, and render it onto the license plate area. If the defined relationship type is "business partner" and the associated scenario is "business reception," another rule might instruct the system to use a simple and professional style, such as a space gray background, elegant thin font, and add a welcome message above the license plate (such as "WELCOME, MR. WANG"). After determining the license plate style, it can be displayed on in-vehicle screens, mobile devices, projected onto the windshield area, or on a welcome display area outside the vehicle, completing the adaptation and presentation of the license plate style.

[0044] Therefore, by relying on users' social relationship data, license plate styles that are adapted to users' social scenarios are automatically generated, eliminating the need for users to manually input and filter personalized needs. This not only reduces the operational cost for users to customize license plate styles, but also allows the customized license plate styles to deeply fit the user's personal social connections, better meeting the user's needs for personalized and emotional expression, improving the intelligence level and user experience of license plate style customization, and solving the problem of license plate style customization being detached from users' actual social scenarios and lacking in personalization.

[0045] According to one embodiment of this application, relationship data is analyzed based on a preset social relationship model to determine the relationship type, including: determining the relationship intimacy index of vehicle users based on the preset social relationship model and relationship data, and determining the relationship type based on the relationship intimacy index, wherein the relationship data includes at least one of vehicle users' address book data, social application interaction records, vehicle sensor data and calendar data.

[0046] Specifically, to further optimize the accuracy of relationship type determination in the above embodiments, this application also provides the following preferred solution. When analyzing relationship data based on a preset social relationship model to determine the relationship type, the relationship intimacy index of vehicle users is first determined based on the preset social relationship model and relationship data, and the relationship type can be determined based on this relationship intimacy index. The relationship data includes at least one of the vehicle user's contact list data, social application interaction records, vehicle sensor data, and calendar data. This limitation aims to introduce a quantitative indicator, so that the classification of relationship types no longer relies on qualitative judgment or simple label matching, but has a calculable and comparable numerical basis, thereby enabling a more nuanced portrayal of the differences in closeness between users and different social relationship objects.

[0047] For example, for a contact marked as a colleague in the address book, if social application interaction records show frequent daily communication and vehicle sensors show multiple ride-sharing records per week, the preset social relationship model might assign that contact a high intimacy index and upgrade their relationship type from a simple colleague to a close friend or close partner. Conversely, if a contact has address book records but almost no interaction, their intimacy index is low, and the relationship type may remain that of a casual friend. By introducing the quantitative indicator of relationship intimacy index, the system can more subtly depict the differences in closeness between users and different social relationships, automatically identifying the closest core relationships and prioritizing them in style generation. Those skilled in the art will understand that alternative methods to achieve the same purpose include directly utilizing user-manually set intimacy levels (e.g., 1-5 stars) or based on publicly available interaction points on social platforms. For example, users can manually set levels such as "very important," "important," and "normal" for specific contacts on the system interface.

[0048] For example, after receiving aggregated multi-source relationship data, the pre-defined social relationship model preprocesses the data and assigns a closeness index calculation task to each contact. This index is derived by weighting the frequency of calls, duration of time spent together, frequency of interactions, and number of shared schedules between the user and a specific contact. The weight parameters are preferably selected between 0 and 1, but a dynamic weight calculation method based on Bayesian networks can also be used.

[0049] It should be noted that the sources of relationship data are not limited to the above-mentioned types, and can also be extended to email communication records, joint online game records, etc., depending on the actual application scenario.

[0050] Therefore, the intimacy index calculated by pre-setting social relationship models and relationship data can more accurately reflect the actual closeness of relationships between different vehicle users, avoiding judgment bias caused by a single data source or fixed grouping. This makes the subsequent license plate style matching more in line with the user's actual social needs and emotional preferences, and makes the generated license plate style more in line with the user's positioning of the relationship object, thereby improving the personalization of license plate style matching and user satisfaction.

[0051] According to one embodiment of this application, determining the relationship intimacy index of vehicle users based on a preset social relationship model and relationship data includes: determining the call frequency, co-existence duration, and interaction records between the vehicle user and each social relationship object based on the relationship data; and calculating the corresponding relationship intimacy index through the social relationship model based on at least one of the call frequency, co-existence duration, and interaction records.

[0052] Specifically, to further refine the calculation method of the relationship intimacy index in the above embodiments, this application also provides the following preferred solution. When determining the relationship intimacy index of vehicle users based on a preset social relationship model and relationship data, the call frequency, co-existence duration, and interaction records between the vehicle user and each social relationship object can be determined first based on the relationship data. Then, based on at least one of the call frequency, co-existence duration, and interaction records, the corresponding relationship intimacy index is calculated through the preset social relationship model. This limitation aims to clarify the specific objective parameters for calculating the relationship intimacy index, improving the certainty and scientific nature of the solution. Thus, by using objective and quantifiable indicators such as call frequency, co-existence duration, and interaction records as the calculation basis, the system can stably generate the relationship intimacy index in a data-driven manner, avoiding the uncertainty caused by subjective assignment, thereby improving the repeatability and interpretability of relationship type determination.

[0053] For example, the preset social relationship model incorporates a rule-based or machine learning-based computing engine. After acquiring multi-source relationship data, the model first extracts the call frequency, co-occurrence duration, and interaction records associated with each social relationship object. Call frequency can be defined as the total number of calls or total duration within a certain time period; co-occurrence duration can be defined as the cumulative time spent in the vehicle with the relationship object; interaction records can include the number of messages, likes, comments, and file shares in social applications. This data, after normalization, is then input into the preset social relationship model.

[0054] The preset social relationship model can fuse and calculate these parameters according to a preset algorithm. For example, a weighted summation method can be used to assign different weights (such as 0.3, 0.4, and 0.3) to call frequency, time spent together, and interaction records. Then, the normalized values ​​are multiplied by their corresponding weights and summed to obtain the final relationship intimacy index. A data record table can then be maintained for each social relationship object (e.g., contact A). For call frequency, the system reads the total number of calls and minutes with contact A in the past three months from the communication record module; for time spent together, the system obtains the number of hours that contact A was present in the vehicle at the same time from historical data from vehicle sensors; for interaction records, the system obtains the number of messages exchanged with contact A in the past three months from authorized data from social applications. These three values ​​are normalized and then substituted into a preset formula for calculation. For example, Relationship Intimacy Index = Normalized Call Frequency × Preset Weight + Normalized Time Spent Together × Preset Weight + Normalized Interaction Records × Preset Weight. Preferably, these parameters are updated weekly, but a high-frequency mode with daily dynamic updates can also be used. In addition, the statistical period for call frequency, duration of time spent together, and interaction records is not limited to three months and can be adjusted between one month and six months depending on the actual application scenario.

[0055] In another example, the pre-set social relationship model can employ a probabilistic inference method based on Bayesian networks, comprehensively considering the historical distribution and current values ​​of the aforementioned indicators, and outputting a probability value between 0 and 1 as the relationship intimacy index. In yet another example, the pre-set social relationship model can be a pre-trained neural network model, whose input layer receives feature vectors of call frequency, shared time, and interaction records. After nonlinear transformation in the hidden layer, the output layer outputs a numerical value as the intimacy index. The training data used for model training can come from a large amount of anonymized user behavioral data to ensure the model's universality and accuracy.

[0056] Those skilled in the art will understand that call frequency can also be used as a single indicator, generating a frequency score by statistically analyzing the number of calls and average call duration over the past month; or only co-occurrence time can be used, generating a duration score by statistically analyzing the historical connection duration of in-vehicle Bluetooth devices; or a weighted average method can be used to sum the three indicators according to a preset ratio. For example, the system can set the weight of call frequency to 0.4, the weight of co-occurrence time to 0.4, and the weight of interaction records (such as the number of likes and comments on social media) to 0.2.

[0057] Therefore, by comprehensively calculating objective data from multiple dimensions, the resulting relationship intimacy index can more accurately reflect the actual intimacy between vehicle users and their corresponding social relationships. It avoids misjudgments due to occasional fluctuations in a single indicator, providing a reliable data foundation for matching corresponding license plate styles based on relationship intimacy. This ensures that the final license plate style better meets the actual usage needs and emotional preferences of vehicle users.

[0058] According to one embodiment of this application, relationship data is analyzed based on a preset social relationship model to determine associated scenario information, including: determining the historical co-occurrence travel records and schedule data between the vehicle user and each social relationship object based on the preset social relationship model and relationship data; and determining associated scenario information based on the historical co-occurrence travel records and schedule data.

[0059] Specifically, to further optimize the determination of associated scenario information in the above embodiments, this application also provides the following preferred solution. When analyzing relationship data based on a preset social relationship model to determine associated scenario information, the historical travel records and schedule data between the vehicle user and each social relationship object can be determined first based on the preset social relationship model and relationship data. Then, associated scenario information can be determined based on the historical travel records and schedule data. This limitation aims to provide a scenario context that is more in line with the actual travel situation for the generated virtual license plate style. That is, by utilizing historical travel records and schedule data, the system can extract typical scenarios related to specific social relationship objects from historical behaviors, thereby making the associated scenario information more in line with the actual car use situation and enhancing the matching degree between the license plate style and the current travel activity.

[0060] In other words, the pre-defined social relationship model not only calculates the intimacy index of relationships but also has scenario analysis capabilities. The model internally stores multi-dimensional historical data accumulated by users over time, including historical travel records and schedule data. Historical travel records can be obtained through in-vehicle navigation systems, Bluetooth connection records, or shared location history, recording the date, origin, destination, identities of companions, and purpose of each trip (e.g., commuting, outing, business). Schedule data comes from user-authorized calendar applications and includes event names, times, locations, participant lists, and event type tags.

[0061] For example, when determining associated scenario information, the pre-defined social relationship model first retrieves historical travel records associated with the current social relationship object (e.g., spouse, child, client Mr. Wang) from the relational database. For instance, the model might find that the couple traveled together to a forest park ten times in the past six months, with most of these trips occurring on weekends. Simultaneously, the model searches calendar data and finds multiple events marked as family weekend trips, with the spouse and child among the participants. By performing association analysis and clustering between the types of historical travel destinations and the labels of calendar events, the model can automatically summarize the typical scenarios most frequently associated with this social relationship object, such as weekend family outings. Similarly, for client Mr. Wang, the model might find that related travel records mostly point to airports or business districts, and that there are business meeting events in the calendar, thus determining the associated scenario information as business reception. The above analysis process is preferably performed when the vehicle is not in motion (e.g., while charging), but real-time streaming computing can also be used. Furthermore, the time frame for tracing historical travel records is not limited to six months and can be adjusted between one month and one year depending on the actual application scenario.

[0062] Those skilled in the art will understand that the scenario can also be determined solely based on the type of destination in historical travel trajectories. For example, if two people repeatedly visit the same amusement park together, the associated scenario information can be identified as family entertainment. Alternatively, the scenario can be determined solely based on the tags in the schedule data. For instance, if the schedule description contains the word "meeting," the associated scenario information can be identified as business. For example, the system can extract a list of destinations that the user and contact A have traveled to together in the past six months from the navigation history, analyze the types of these destinations (such as residential areas, parks, business districts, and airports), and, combined with the schedule event descriptions, summarize typical scenarios.

[0063] Therefore, by deeply mining historical travel and schedule data, we can more accurately capture the real needs of vehicle users in their current travel scenarios, avoid scenario mismatch caused by single-dimensional judgment, and enable the subsequently generated license plate styles to better adapt to the current travel context, thereby improving the accuracy of personalized presentation. At the same time, the solution can flexibly adjust the timing of analysis and the scope of tracing according to computing resources, which can ensure the accuracy of analysis without additionally consuming computing resources during vehicle operation, thus balancing functional effects and system stability.

[0064] According to one embodiment of this application, determining the license plate style based on relationship type and associated scene information includes: determining the license plate style based on relationship type, associated scene information and a preset visual element mapping rule library.

[0065] Specifically, when determining license plate styles based on relationship types and associated scene information, the style can be determined based on the relationship type, associated scene information, and a preset visual element mapping rule library. That is, by introducing a preset visual element mapping rule library, relationship types and scene information can be automatically mapped to corresponding visual elements, achieving automated generation from abstract relationships to specific styles, avoiding manual intervention, and improving customization efficiency and consistency.

[0066] The license plate style is determined using a lookup table. The input is a tuple of (relationship type, scene information), and the output is a set of visual style parameters. This lookup table can be pre-written by engineers or automatically generated by the system based on user feedback regarding specific styles. The preset visual element mapping rule base is preferably updated quarterly, but online dynamic updates are also supported. Furthermore, the mapping rules in the preset visual element mapping rule base are not limited to one-to-one mapping; they can be set to one-to-many mapping as needed, meaning one social status corresponds to multiple selectable styles for the user to choose from.

[0067] Those skilled in the art will understand that the preset visual element mapping rule library may also contain only simple color mappings, such as mapping family relationships to warm colors (red, orange) and business relationships to cool colors (blue, gray); or the rule library may employ a dynamic creation system based on generative adversarial networks, where the system directly generates artistic license plate styles based on relationship description text. For example, a rule in the preset visual element mapping rule library may be defined as follows: if the relationship type is "family" and the scene is "family day", then the output rule ID is FAMILY_001, and its corresponding visual parameters include: the border style is "wood texture", the background image is "latest picture in family album", the font is "round font", and the additional text is "FAMILY TIME".

[0068] Therefore, by pre-setting a visual element mapping rule library, it can ensure that the license plate style output meets expectations under different relationship types and scene combinations. It supports lightweight and rapid customization matching, and can also achieve personalized artistic creation with the help of generative models. It meets the license plate customization needs under different scenarios and technical conditions. At the same time, the dynamically updated rule mechanism can adapt to the ever-changing customization needs of users, further improving the flexibility and adaptability of license plate customization.

[0069] According to one embodiment of this application, the virtual license plate style determination method further includes: when it is determined that the vehicle has entered the privacy protection mode, replacing the license plate style with a preset general style, or hiding the license plate style.

[0070] Specifically, while automatically generating personalized license plate styles, protecting user privacy and preventing the exposure of social relationships in non-private settings is a crucial practical need. To address this issue, in a preferred implementation, when the vehicle is confirmed to be in privacy protection mode, the license plate style can be replaced with a preset universal style or hidden. In other words, by setting the privacy protection mode and its corresponding replacement or hiding operation, the system can automatically block personalized license plate styles in situations where user privacy needs to be protected, preventing social relationship information from being obtained by irrelevant personnel (such as designated drivers or repair technicians), thus improving user data security and user comfort.

[0071] For example, the privacy protection controller receives vehicle permission status signals. Once it receives an instruction to enter privacy protection mode, the controller sends an interrupt signal to the rendering layer. The rendering layer then suspends the generation of personalized relational models and instead reads preset general style data from its internal read-only memory and renders it. Furthermore, the hiding operation can be to display the license plate area in the same color as the main vehicle model to achieve complete visual disappearance, or to display only neutral information such as the vehicle model code.

[0072] Those skilled in the art will understand that it is also possible to simply replace the actual relationship data with fictitious anonymous data (such as generating a "Mr. Zhang" instead of a real name), or to replace the license plate style with a fixed static default style, without displaying any personalized content. For example, when a vehicle enters chauffeur mode, the system immediately replaces the virtual license plate that originally displayed a family photo and heartwarming family text with a gray license plate displaying the three standard Song typeface characters "My Car," while the background changes to a solid color.

[0073] Therefore, it can both preserve the emotional value that personalized license plates bring to users' daily use and block the exposure of personalized information with one click in special scenarios where the right to use the vehicle needs to be shared with others. It balances the needs of personalized experience and privacy and security, and will not reduce users' willingness to use personalized license plates due to privacy concerns. At the same time, it has low implementation cost, does not require additional hardware modifications to the existing in-vehicle display system, and has strong adaptability.

[0074] According to one embodiment of this application, the virtual license plate style determination method further includes: acquiring physiological state data or emotional state data of vehicle users; and dynamically adjusting the visual style of the license plate style based on the physiological state data or emotional state data, wherein the visual style includes at least one of color tone, pattern complexity, or animation speed.

[0075] Specifically, to further optimize the real-time adaptation capability of license plate styles in the above embodiments and enable the virtual license plate display to more subtly reflect the current psychological state of the vehicle user, this application also provides the following preferred solution. As mentioned above, after determining the license plate style based on relationship type and associated scenario information, an initial style highly coupled with the social context has been generated. However, the real-time emotions or physiological state of the vehicle user will also affect their perception and acceptance of visual content. For example, when in a good mood, users may prefer bright and lively visual effects; while when tired or tense, a soft and simple style may be more suitable.

[0076] First, data on the vehicle user's physiological or emotional state is acquired. Then, based on this data, the visual style of the license plate is dynamically adjusted. The visual style includes at least one of the following: color scheme, pattern complexity, or animation speed. This limitation aims to expand the generation of customized styles from solely relying on social relationships and contextual information to integrating the user's current physiological and emotional state, thereby achieving a higher level of personalized and emotional interaction.

[0077] For example, physiological state data can be acquired through in-vehicle sensors. For instance, capacitive sensors on the steering wheel can detect the driver's heart rate and skin conductivity; in-vehicle cameras can use non-contact photoplethysmography to monitor heart rate variability and respiratory rate; and seat pressure sensors can analyze the driver's posture and body sway. Emotional state data can be inferred in various ways: for example, by collecting user voice data through in-vehicle microphones and using voice emotion recognition models to analyze features such as tone, speed, and volume to infer emotion categories such as happiness, calmness, anxiety, and anger; by capturing user facial expressions through facial cameras and using expression recognition algorithms to determine emotional state; or indirectly by observing user interactions with the in-vehicle system (such as interface click frequency and the urgency of voice commands).

[0078] After acquiring physiological or emotional state data, the system passes it as input parameters to the style generation engine or a custom rule base, triggering the generation of new dynamic adjustment instructions. For example, if the system detects a significant increase in the driver's physiological data (such as heart rate and skin conductivity) and voice analysis shows a rapid tone, the system determines that the user is currently in a state of anxiety or tension. In this case, the dynamic adjustment rules can instruct the system to adjust the color tone of the already generated license plate style from a highly saturated warm tone to a soft neutral or cool tone to create a soothing visual atmosphere; at the same time, the complexity of the pattern is reduced (e.g., removing flashing elements and complex textures from the animated background), and the animation speed is slowed down or paused completely to avoid causing additional visual interference to the user. Conversely, if the system detects a user smiling and having a stable heart rate through facial expression recognition, or identifies a pleasant tone through voice analysis, it determines that the user is in a positive emotional state. At this point, the system can adjust the color tone of the style to brighter, more vibrant colors (such as gold or orange), increase the fun and complexity of the pattern (for example, by adding dynamic particle effects or cheerful cartoon elements), and appropriately increase the playback speed of the animation to enhance the cheerful atmosphere.

[0079] This enables the perception and response to the user's real-time physical and mental state, making the virtual license plate not just a static social identifier, but a dynamic digital companion that can resonate with the user's emotions. It also helps to solve the problem of existing customized interfaces being disconnected from the user's real feelings and lacking emotional feedback.

[0080] According to one embodiment of this application, the virtual license plate style determination method further includes: acquiring external environment information, the external environment information including at least one of light intensity, weather conditions, or surrounding vehicle density; and adjusting the display parameters of the license plate style based on the external environment information, the display parameters including at least one of brightness, color saturation, and transparency.

[0081] Specifically, to further enhance the display effect and user experience of virtual license plates in different external environments, and to ensure that users can obtain a clear, comfortable, and safe visual experience under any lighting, weather, or traffic conditions, this application also provides the following preferred solutions. In the above embodiments, the determination of the license plate style mainly depends on the user's social relationships, scene information, and physiological / emotional state. However, external environmental factors (such as light intensity, weather changes, and surrounding vehicle density) can also significantly affect the visibility and visual interference of the content rendered on the digital interface. For example, in direct sunlight or at night, high-brightness license plate styles may cause glare that interferes with driving safety; in rainy or foggy weather, low-contrast styles may be difficult to identify; and in dense traffic environments, overly complex or dynamic styles may distract the driver.

[0082] First, external environmental information is acquired, including at least one of light intensity, weather conditions, or surrounding vehicle density. Then, based on this information, the display parameters of the license plate style are adjusted, including at least one of brightness, color saturation, and transparency. This limitation aims to incorporate real-time changes in the external environment into the dynamic adjustment of the style, thereby ensuring the safety and adaptability of the display effect while maintaining personalized expression.

[0083] For example, external environmental information can be acquired through onboard sensors and communication modules. Light intensity can be obtained through ambient light sensors located outside the vehicle or through photoelectric sensors that detect the light transmittance of the windshield, with output values ​​in the lux range. Weather conditions can be determined by combining rain sensors (detecting raindrop frequency), temperature sensors, barometric pressure sensors, and real-time weather data obtained from onboard weather services or the cloud, to determine whether the current weather is sunny, cloudy, rainy, snowy, or foggy. Surrounding vehicle density can be detected through image recognition analysis using onboard cameras to detect the number and distance of vehicles in front, to the sides, and behind, or by obtaining surrounding vehicle distribution data through vehicle-to-everything (V2X) communication, thereby deriving a quantitative density level (e.g., sparse, normal, crowded).

[0084] After acquiring external environmental information, the system passes it as input parameters to the display parameter adjustment module. This module can be integrated into the rendering layer or operate independently of the style generation engine, serving as a post-processing step to fine-tune the generated license plate style. For example, when the ambient light sensor detects that the light intensity is below a preset threshold (e.g., entering a tunnel or driving at night), the system automatically increases the brightness of the license plate style to a comfortable level (e.g., increasing the RGB values ​​of pixels) and appropriately increases color saturation to maintain its legibility, while reducing transparency to ensure that the contrast between the license plate text and the background meets readability standards. When the rain sensor detects rain, the system automatically reduces color saturation to avoid unnatural reflections from highly saturated colors in the rain, while appropriately reducing brightness and animation speed to minimize visual interference. When the camera detects congested surrounding traffic (e.g., multiple vehicles entering a highway side-by-side), the system automatically sets the style's transparency to semi-transparent or reduces its brightness to a level close to the background, making the license plate content less prominent and thus avoiding distracting the driver. After the vehicle leaves the congested area, the system restores the display parameters to normal levels.

[0085] The aforementioned adjustments can be real-time and continuous, and can work in conjunction with the emotional state adjustments described in the previous embodiments. For example, at night when the user is emotionally stressed, the system can simultaneously reduce brightness, saturation, and animation speed to create the most tranquil and safe visual environment. The specific values ​​of the adjustment parameters can be implemented using pre-calibrated lookup tables or rule-based logic circuits, or they can be personalized through machine learning models based on the user's historical feedback.

[0086] This enables virtual license plate styles to adaptively respond to changes in the external environment, ensuring a clear, comfortable, and safe display under any driving conditions. This further helps to solve the visual discomfort or safety hazards that may result from fixed-style virtual license plates in dynamic driving environments.

[0087] According to one embodiment of this application, the virtual license plate style determination method further includes: upon receiving an authorization instruction from a vehicle user or detecting that a vehicle has entered a preset geographical area, determining to enter a privacy protection mode, wherein the preset geographical area includes the coverage area of ​​a chauffeur service platform or the vehicle repair service area.

[0088] Specifically, to further refine the triggering conditions of the privacy protection mode in the above embodiments, this application also provides the following preferred solution. Upon receiving an authorization command from the vehicle user or detecting that the vehicle has entered a preset geographical area, the system can determine whether to enter the privacy protection mode. The preset geographical area includes the coverage area of ​​the chauffeur service platform or the vehicle repair service area. Thus, through either an authorization command or a preset geographical area triggering method, the system can automatically identify typical scenarios requiring privacy protection without requiring manual user operation, achieving intelligent triggering of privacy protection, ensuring both convenience and improved reliability.

[0089] For example, the system's state decision module receives two types of input: first, an authorization command signal from the user's mobile terminal (which is authenticated and encrypted); and second, location data from the vehicle's positioning module. The state decision module compares the current location with a pre-stored "sensitive area" geofence database. If a match is found, the state decision module outputs a high-level switching control signal to the privacy protection controller. The update permission for the aforementioned geofence database is preferably reserved for the vehicle owner, but data pushes from official service applications are also supported. Furthermore, the preset geographical range is not limited to chauffeur and repair areas and can be extended to gas stations, public parking lots, etc., depending on the actual situation.

[0090] Those skilled in the art will understand that the system can also be triggered when the in-vehicle camera detects a mismatch between the driver's and the pre-registered vehicle owner's facial features, or when a connection request from an unfamiliar Bluetooth device is detected. For example, before the chauffeur service begins, the vehicle owner can click the "Chauffeur Mode" button with a single tap on a mobile application; this instruction is sent to the vehicle via a cloud server. Alternatively, when the vehicle enters a geofenced area pre-marked as an "authorized service center" in the system, the system automatically triggers privacy protection.

[0091] Therefore, in scenarios where vehicle operation rights are handed over to others, the original owner's personal information can be automatically hidden to avoid privacy leaks, while not affecting the normal operation of services such as chauffeur services and repairs. This enhances the security of users' personal information while ensuring service convenience.

[0092] According to one embodiment of this application, the virtual license plate style determination method further includes: receiving a user's social relationship selection instruction; and generating a license plate style based on the social relationship selection instruction.

[0093] Specifically, in addition to automatically generating license plate styles, it is equally important to meet users' needs for manually customizing social relationships. To address this issue, in a preferred embodiment, the system can also receive users' social relationship selection instructions and generate license plate styles based on these instructions. This limitation aims to provide an interface for user intervention, balancing automatic recommendations with user control. By allowing users to actively select the social relationships to be displayed, the system provides a means of manual intervention, enabling users to flexibly customize according to their own wishes beyond automatic recommendations, thus enhancing the autonomy and personalized control of the interaction.

[0094] For example, the human-computer interaction module continuously listens for the user's touch or voice input. Upon receiving a social relationship selection instruction to choose "Friend Mode," the instruction is parsed and passed to the relationship modeling engine. Based on the keywords in the instruction, the engine retrieves relationship data related to the "Friend" type from the relationship model and extracts potentially relevant scene tags (such as a weekend night). The retrieval results are then submitted to a custom rule base for style generation. Furthermore, the input format for social relationship selection instructions is not limited to clicks and voice; gesture control or eye tracking can be supported as needed.

[0095] Those skilled in the art will understand that users can also directly say "I want to display family mode" via voice command, and the system will execute the command after recognition; or users can select the social relationships they want to display from a list on the central control screen. For example, a "Social Mode Selection" menu can be provided on the main interface of the vehicle system, listing options such as "Family Mode," "Friends Mode," and "Business Mode," which users can select to activate. When the user selects "Friends Mode," the system immediately generates the corresponding license plate style based on the relationship data about close friends in the relationship model and the corresponding scene tags (such as friends gathering), calling the customized rule library.

[0096] As a result, users can choose a license plate display style that matches their current social relationship based on different travel scenarios and companions. This not only allows the license plate style to better match the travel atmosphere, but also meets users' personalized display needs in different social scenarios, further improving the flexibility of license plate style customization and user experience. At the same time, it makes the interactive functions of the smart car system more in line with users' actual usage habits, and strengthens the adaptability of the vehicle to users' social needs.

[0097] According to one embodiment of this application, displaying a license plate based on a license plate style includes rendering the license plate style onto a virtual vehicle model in a digital interface.

[0098] Specifically, when displaying license plate designs, the designs can be rendered onto a virtual vehicle model within the digital interface. This limitation aims to explicitly confine the display of customized content to the virtual digital space, fundamentally mitigating legal risks. By rendering the license plate design onto the virtual vehicle model, the system clearly restricts customized content to the digital display interface, strictly distinguishing it from physical license plates. This ensures full compliance with road traffic safety regulations while achieving personalized expression, eliminating legal risks.

[0099] For example, the rendering engine receives a license plate style data packet containing all visual parameters. The rendering engine binds the 3D vehicle model to the license plate texture and performs real-time rendering via the graphics processor, ultimately generating a display frame. Furthermore, the digital interface is not limited to in-vehicle screens and can be extended to any digital display medium, such as mobile applications and smartwatches, depending on the specific needs.

[0100] Those skilled in the art will understand that it can also be rendered in a separate floating window on an in-vehicle display or overlaid on an actual vehicle model in an augmented reality head-up display. For example, when a user views a 3D model of their vehicle in a mobile application, the system maps the virtual license plate style as a separate texture map precisely to the license plate location on the model. The words "This is a virtual display" are displayed in a semi-transparent font in the corner of the display interface.

[0101] Therefore, it not only allows users to intuitively preview the presentation effect of personalized license plate styles and meet their personalized customization preview needs, but also keeps the display of personalized styles within a virtual digital scene, without affecting the compliance of physical license plates. This completely avoids the possibility of illegally using personalized license plates on the road. While meeting users' personalized experience needs, it strictly complies with the current traffic management regulations and requirements, balancing user experience and compliance requirements.

[0102] In summary, as a specific example, on a weekend morning, car owner Zhang San enters his vehicle with his wife and son. The vehicle confirms Zhang San's ownership via its facial recognition camera and simultaneously identifies his wife and son's accounts as connected to the in-vehicle system via Bluetooth. The vehicle's status perception module further detects that the navigation destination is set to "XX Forest Park." This information is transmitted in real-time to a preset social relationship model. Based on Zhang San's identity, the preset social relationship model immediately retrieves his authorized relationship data, discovering that his spouse and child have a very high relationship intimacy index and multiple shared trips to the suburbs in their historical travel records. The system thus classifies the relationship type as "family" and the associated scenario as a weekend family outing. Based on this, a preset visual element mapping rule library instructs the system to select a recent, heartwarming family photo from the family cloud album and process it in a cartoon style; another rule specifies that the license plate border should use a wood grain or grass texture to match the natural setting of the outing. The final generated virtual license plate design appears as a dynamic frame: a cartoon-style family portrait is displayed in the center, with "FAMILY TRIP" scrolling below the license plate number. Upon vehicle startup, a miniature entrance animation is triggered. This virtual license plate design is then rendered onto the license plate area of ​​the 3D virtual vehicle model on the in-car screen, displaying a "This is a virtual display" sign. This scenario creates a personalized and warm atmosphere for users from the moment they enter the car, imbuing the journey with a sense of ritual and family belonging from the very beginning, significantly enhancing the emotional interaction experience of the smart cockpit.

[0103] As another concrete example, car owner Zhang San's schedule includes an event related to "picking up client Mr. Wang at the airport." When the vehicle arrives at the airport parking lot, the system determines the current scenario as a business reception through geolocation recognition or Zhang San's manually activated "business reception mode." The preset social relationship model retrieves Zhang San's client Mr. Wang's relationship data based on his identity and determines the relationship type as business partner. The style generation module then calls the "professional, prestigious" style template from the custom rule library. If the system can obtain the client company's brand color, it is associated with the license plate background color; otherwise, space gray is used as the default background. The license plate number uses an elegant, thin font, with a line of small text, such as "WELCOME, MR. WANG," displayed above or below the license plate. The rendered virtual license plate presents an overall digital prestigious business card. In this scenario, the user can demonstrate exceptional care and professionalism before the client even gets in the car, thereby enhancing their business image and improving the goodwill of potential partners.

[0104] As another concrete example, Zhang San created a "May Day Sichuan-West Trip" carpool using an in-car social application and associated it with the vehicles of his fellow travelers. The preset social relationship model, based on Zhang San's identity, retrieved his friends' relationship data, determined the relationship type to be friends / carpool, and associated the scenario information as multi-vehicle travel. The style generation module called a custom rule library to generate a unified virtual carpool identifier for the entire carpool. This identifier was applied to the license plates of all carpool members' virtual vehicle models, specifically by displaying a unified carpool badge (such as a simple line drawing of a mountain containing the numbers "05.01") in a fixed position on the license plate, with a uniform, vibrant orange border. Furthermore, on the in-car map, each vehicle's identifier also simultaneously displayed this badge. In this scenario, even if the vehicles were scattered in traffic, users could quickly find their companions through this unique virtual identifier, thereby strengthening a sense of team belonging and enhancing the enjoyment of the journey.

[0105] As another concrete example, the vehicle status perception module detects that Zhang San has just achieved a record of over 600 kilometers of range on a single charge, or that his driving score has reached "S" level for a week consecutively. The system automatically identifies this event as a "personal achievement" scenario. The preset social relationship model determines the relationship type as "self," and the scenario information as "personal achievement." The style generation module calls the "celebration" style package from the rule library. The generated virtual license plate style appears as a miniature achievement display window: the background has a twinkling star animation, the license plate number is surrounded by small trophy or medal icons, and displays words such as "600km CHAMPION!" or "S-WEEK!". This style automatically returns to normal after being displayed for a period of time. In this scenario, the vehicle becomes a partner in recording and celebrating personal milestones, providing users with gamified positive feedback and a sense of exclusive honor.

[0106] The following is combined Figure 2 The method described in this application is used to describe the method.

[0107] As a specific example, the method for determining the virtual license plate style in this application may include the following steps: S101 identifies the vehicle user's identity.

[0108] S102, Obtain relationship data of social relationship objects associated with the identity identifier.

[0109] S103, determine the relationship intimacy index of vehicle users based on the preset social relationship model and relationship data, and determine the historical travel records and schedule data of vehicle users and each social relationship object based on the preset social relationship model and relationship data.

[0110] S104 determines the relationship type based on the relationship intimacy index and determines the associated scenario information based on historical travel records and schedule data.

[0111] S105 determines the license plate style based on relationship type, associated scene information, and a preset visual element mapping rule library.

[0112] S106 renders the license plate style onto the virtual license plate display box on the virtual vehicle model in the digital interface.

[0113] In summary, the virtual license plate style determination method according to the embodiments of this application identifies the vehicle user's identity, obtains relationship data of social relationships associated with the identity, analyzes the relationship data based on a preset social relationship model to determine the relationship type and associated scenario information. The preset social relationship model is pre-determined based on the relationship data and according to preset relationship analysis rules, and is used to characterize the degree of association and scenario relevance between the vehicle user and each social relationship object. The license plate style is determined based on the relationship type and associated scenario information, and then displayed in a virtual license plate display frame based on the license plate style. Therefore, this method can meet the user's needs for personalized and emotional expression, improving the intelligence level of license plate style customization and user experience.

[0114] Corresponding to the above embodiments, this application also proposes a vehicle.

[0115] like Figure 3 As shown, the vehicle 200 in this embodiment may include: a memory 210, a processor 220, and a program stored on the memory 210 and executable on the processor 220. When the processor 220 executes the program, it implements the above-described virtual license plate style determination method.

[0116] According to the embodiments of this application, by executing the above-described virtual license plate style determination method, the vehicle can meet the user's needs for personalized and emotional expression, and improve the intelligence level of license plate style customization and user experience.

[0117] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0118] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0119] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0120] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0121] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0122] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for determining the style of a virtual license plate, characterized in that, The method, applied to an intelligent cockpit system, displays a virtual vehicle model on its digital interface, and includes a virtual license plate display frame on the virtual vehicle model. Identify the vehicle user's identity; Obtain relationship data of social relationship objects associated with the identity identifier; The relationship data is analyzed based on a preset social relationship model to determine the relationship type and associated scenario information. The preset social relationship model is determined in advance based on the relationship data and according to preset relationship analysis rules. It is used to characterize the degree of association and scenario association between the vehicle user and each social relationship object. The license plate style is determined based on the relationship type and the associated scenario information, and then displayed in the virtual license plate display frame based on the license plate style.

2. The method for determining the virtual license plate style according to claim 1, characterized in that, The relationship data is analyzed based on a pre-defined social relationship model to determine the relationship type, including: The relationship intimacy index of the vehicle user is determined based on the preset social relationship model and the relationship data, and the relationship type is determined based on the relationship intimacy index. The relationship data includes at least one of the vehicle user's address book data, social application interaction records, vehicle sensor data, and calendar data.

3. The method for determining the virtual license plate style according to claim 2, characterized in that, The step of determining the relationship intimacy index of the vehicle users based on the preset social relationship model and the relationship data includes: Based on the relationship data, the frequency of calls, duration of time spent together, and interaction records between the vehicle user and each social relationship object are determined. The corresponding relationship intimacy index is calculated based on at least one of the call frequency, the duration of time spent together, and the interaction records, using the preset social relationship model.

4. The method for determining the virtual license plate style according to claim 1, characterized in that, The relationship data is analyzed based on a pre-defined social relationship model to determine associated scenario information, including: Based on the preset social relationship model and the relationship data, determine the historical travel records and schedule data of the vehicle user and each social relationship object; The associated scenario information is determined based on the historical travel records and the schedule data.

5. The method for determining the virtual license plate style according to claim 2, characterized in that, Determining the license plate style based on the relationship type and the associated scenario information includes: The license plate style is determined based on the relationship type, the associated scene information, and the preset visual element mapping rule library.

6. The method for determining the virtual license plate style according to claim 5, characterized in that, The method further includes: If the vehicle is confirmed to be in privacy protection mode, the license plate style will be replaced with a preset general style, or the license plate style will be hidden.

7. The method for determining the virtual license plate style according to claim 6, characterized in that, The method further includes: Upon receiving an authorization instruction from the vehicle user, or upon detecting that the vehicle has entered a preset geographical area, the system determines to enter a privacy protection mode. The preset geographical area includes the coverage area of ​​the chauffeur service platform or the vehicle repair service area.

8. The method for determining the virtual license plate style according to claim 1, characterized in that, The method further includes: Acquire the physiological or emotional state data of the vehicle user; Based on the physiological or emotional state data, the visual style of the license plate is dynamically adjusted, and the visual style includes at least one of color tone, pattern complexity, or animation speed.

9. The method for determining the virtual license plate style according to claim 1, characterized in that, The method further includes: Acquire external environmental information, which includes at least one of light intensity, weather conditions, or surrounding vehicle density; Based on the external environment information, the display parameters of the license plate style are adjusted, and the display parameters include at least one of brightness, color saturation, and transparency.

10. A vehicle, characterized in that, include: The system includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the virtual license plate style determination method according to any one of claims 1-9.

Images