Self-adaptive display method and system of vehicle-mounted QD-MicroLED screen

Abstract

The invention relates to the technical field of display control, in particular to a self-adaptive display method and system for a vehicle-mounted QD-MicroLED screen, and the method comprises the steps: obtaining original monitoring data collected by a vehicle-mounted sensing module, carrying out the analysis of a scene where a vehicle is located according to the original monitoring data, so as to obtain the operation scene information of the vehicle, and carrying out the display of the vehicle-mounted QD-MicroLED screen. Analyzing the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the operation scene information to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen, acquiring scene visual data collected by a vehicle-mounted visual module, and performing adaptability analysis of a content rendering mode on the scene visual data according to the display priority standard to obtain the scene display content of the vehicle-mounted QD-MicroLED screen. And generating an optimal content rendering mode so as to carry out content rendering on subsequent scene visual data.

Description

Technical Field

[0001] This application relates to the technical field of display control, and in particular to an adaptive display method and system for an in-vehicle QD-MicroLED screen. Background Technology

[0002] During driving, drivers need to quickly and accurately obtain key information, such as vehicle speed, navigation instructions, and warning information. Traditional fixed display modes cannot clearly and efficiently display this information in different scenarios. Different environmental conditions (such as daytime, nighttime, strong light, and weak light) will affect the visual effect of the in-vehicle display screen, causing drivers to spend more time and energy to find and understand the required information, which increases driving risks. Summary of the Invention

[0003] Therefore, it is necessary to provide an adaptive display method and system for vehicle-mounted QD-MicroLED screens to address the aforementioned technical issues. This system can dynamically adjust the priority and rendering method of the displayed content according to the scene, thereby improving information acquisition efficiency and ensuring driving safety.

[0004] In a first aspect, this application provides an adaptive display method for an in-vehicle QD-MicroLED screen, the method comprising: The aforementioned adaptive display method for in-vehicle QD-MicroLED screens analyzes sensor data to clearly define the operating scenario, enabling precise adaptation to display requirements. Based on this, the determined display priority standard prioritizes the presentation of important information, improving information acquisition efficiency. By generating the optimal rendering mode based on the standard, visual data can be rendered in different scenarios, optimizing display effects and ensuring visual comfort. It also reduces unnecessary information interference, allowing drivers to focus on road conditions and improving driving safety. At the same time, it fully leverages the advantages of QD-MicroLED screens to deliver a better interactive experience.

[0005] Secondly, this application also provides an adaptive display system for an in-vehicle QD-MicroLED screen, used to implement the adaptive display method for an in-vehicle QD-MicroLED screen as described in any one of the first aspects, comprising: The scene monitoring module is used to acquire the raw monitoring data collected by the vehicle-mounted sensing module and analyze the scene in which the vehicle is located based on the raw monitoring data to obtain the vehicle's operating scene information. The priority analysis module is used to analyze the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the operation scene information, so as to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen. The mode selection module is used to acquire scene visual data collected by the vehicle vision module, and perform an adaptive analysis of the content rendering mode on the scene visual data according to the display priority standard to generate the optimal content rendering mode for subsequent scene visual data content rendering.

[0006] The aforementioned adaptive display method for in-vehicle QD-MicroLED screens analyzes sensor data to clearly define the operating scenario, enabling precise adaptation to display requirements. Based on this, the determined display priority standard prioritizes the presentation of important information, improving information acquisition efficiency. By generating the optimal rendering mode based on the standard, visual data can be rendered in different scenarios, optimizing display effects and ensuring visual comfort. It also reduces unnecessary information interference, allowing drivers to focus on road conditions and improving driving safety. At the same time, it fully leverages the advantages of QD-MicroLED screens to deliver a better interactive experience. Attached Figure Description

[0007] Figure 1 This is a schematic diagram illustrating the steps of an adaptive display method for an in-vehicle QD-MicroLED screen in one embodiment; Figure 2 This is a schematic diagram of the structure of an adaptive display system for an in-vehicle QD-MicroLED screen in one embodiment. Detailed Implementation

[0008] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0009] The adaptive display method for vehicle-mounted QD-MicroLED screens provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown: S1: Obtain the raw monitoring data collected by the vehicle-mounted sensor module, and analyze the vehicle's location based on the raw monitoring data to obtain the vehicle's operating scenario information. S2: Based on the aforementioned operating scenario information, analyze the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen; S3: Acquire scene visual data collected by the vehicle vision module, and perform adaptive analysis of the content rendering mode on the scene visual data according to the display priority standard to generate the optimal content rendering mode for subsequent scene visual data content rendering.

[0010] Specifically, in step S1 of the embodiments provided in this application, the vehicle-mounted sensing module is typically composed of a variety of sensors, such as speed sensors, acceleration sensors, temperature sensors, humidity sensors, light sensors, and radar sensors. These sensors can monitor the vehicle's status and surrounding environment from different dimensions. The speed sensor can measure the vehicle's speed, and the acceleration sensor can detect the vehicle's acceleration or deceleration state, which is crucial for determining whether the vehicle is traveling at high speed, low speed, or stationary. The temperature and humidity sensors can acquire temperature and humidity information of the vehicle's surrounding environment, which helps determine whether the vehicle is in a hot and dry desert area, a cold and humid mountain area, or a mild urban environment. The light sensor can sense the ambient light intensity and distinguish between different lighting conditions such as daytime, nighttime, and cloudy days. The radar sensor can detect the distance and relative speed between the vehicle and surrounding obstacles, which is used to determine whether the vehicle is in a congested road section, parking lot, or other similar scenario.

[0011] More specifically, the scene type of the vehicle is located is analyzed based on the various monitoring items contained in the original monitoring data, and the scene type code corresponding to the analysis result is retrieved from the preset coding library. For example, if the speed sensor shows that the vehicle speed is 0 and the radar sensor detects dense obstacles around the vehicle, combined with the map information of the parking lot, it can be determined that the vehicle is in a parking lot scene. Then, the code corresponding to "parking lot scene" is retrieved from the preset coding library. Different monitoring items can provide different clues for the determination of scene type. Through comprehensive analysis of these clues, the scene type can be determined more accurately.

[0012] More specifically, the interaction and correlation of the coding of each scene type are analyzed to obtain the information correlation between the information fed back by each scene type coding. For example, there is a strong correlation between the coding of "night scene" and "low light intensity scene" because night is usually accompanied by low light intensity. Understanding these information correlation forms helps to understand the scene in which the vehicle is located more comprehensively and avoid one-sided judgment of the scene.

[0013] More specifically, based on information association, mutually exclusive content is removed and related content is expanded from the feedback information of each scene type code. This involves retrieving several scene type codes with corresponding adjusted content from a preset code library and simultaneously generating fusion weights for each scene type code. For example, if there is some overlap between the "rainy day scene" code and the "wet environment scene" code, the duplicate information needs to be removed. At the same time, if a strong correlation is found between "rainy day scene" and "slippery road scene", the "rainy day scene" code can be expanded to include information related to slippery roads. Generating fusion weights for each scene type code is to allow for reasonable weighting based on the importance of each code when combining scene characteristics in the future, so that the final scene characteristics more accurately reflect the actual scene in which the vehicle is located. The scene type code is combined with the corresponding fusion weight to form a scene characteristic. The resulting scene characteristic can comprehensively reflect multiple aspects of the scene in which the vehicle is located, and the relative importance of each characteristic is reflected through the fusion weight.

[0014] More specifically, by integrating the characteristics of various scenarios, a complete vehicle operation scenario information is formed. Different scenario characteristics describe the scenario in which the vehicle is located from different perspectives. Combining them can yield a comprehensive and accurate description of the vehicle operation scenario. For example, by combining the characteristics of "parking lot scenario", "low light intensity scenario" and "humid environment scenario", we can obtain the operation scenario information of the vehicle currently in a dimly lit and humid parking lot.

[0015] More specifically, vehicle operating scenarios are a complex concept, influenced by a combination of factors. Multi-dimensional data monitoring can acquire as much relevant information as possible, avoiding misjudgments of scenarios due to missing information. Simply acquiring raw monitoring data is insufficient; in-depth analysis and processing are necessary to extract key scenario characteristics and generate accurate operating scenario information through reasonable combinations. This provides a reliable basis for determining subsequent display priority standards and selecting content rendering modes. Different operating scenarios have different requirements for the content displayed on the in-vehicle display touch module. In high-speed driving scenarios, users are more concerned with navigation information and vehicle speed; while in parking lot scenarios, users need to view surrounding parking space information. Accurate operating scenario information enables in-vehicle display content to better adapt to different scenarios, improving the user experience.

[0016] Specifically, in step S2 of the embodiment provided in this application, the scene display priority framework is pre-built. It stores the display priority standards of the vehicle QD-MicroLED screen under different preset operating scenarios. This framework is deployed locally in the vehicle so that it can be quickly retrieved and used when needed. This framework can be obtained through a large number of experiments, data analysis and research on user needs, etc., and covers various possible vehicle operating scenarios, including display priority rules for different scenarios such as urban road driving, highway driving, parking lot parking, and night driving.

[0017] More specifically, the current vehicle operation scenario information is compared and analyzed with the preset operation scenarios in the scenario display priority framework. Since the actual operation scenario may not be completely consistent with the preset scenario, it is necessary to find the closest preset scenario and determine the correlation between them. The current operation scenario is encountering slight congestion on urban roads, with a slow vehicle speed and many pedestrians around. The scenario display priority framework has preset scenarios such as "urban road congestion scenario" and "urban road normal driving scenario". Through comparative analysis, it is determined that the current scenario is more correlated with the "urban road congestion scenario".

[0018] More specifically, based on the scene correlations analyzed above, the display priority standard of the most matching preset operating scene is selected from the scene display priority framework. However, since there are some subtle differences between the actual scene and the preset scene, the selected display priority standard needs to be adaptively adjusted. In the preset "urban road congestion scene" display priority standard, navigation information and vehicle fault prompt information are placed in the highest priority display position by default. However, in the current actual urban road slight congestion scene, considering that there are many pedestrians around, the display priority of pedestrian warning information needs to be appropriately increased. The original display priority standard is fine-tuned to obtain a display priority standard for the vehicle QD-MicroLED screen that is more in line with the current actual operating scene.

[0019] More specifically, by pre-deploying a scene display priority framework locally on the vehicle, complex calculations and analyses are avoided each time display priority criteria need to be determined. Relevant information can be quickly retrieved from local storage, significantly reducing processing time and ensuring the system can respond promptly to changes in vehicle operating scenarios, providing users with real-time and accurate display content. The scene display priority framework, derived from extensive experimentation and data accumulation, integrates optimal display strategies for various scenarios. By retrieving this framework, previous research findings and experience can be fully utilized, improving the accuracy and reliability of determining display priority criteria.

[0020] More specifically, actual vehicle operation scenarios are highly variable, making it difficult to find a completely identical situation within a preset scenario. By analyzing scenario relationships, we can identify the preset scenario that is closest to the current operating scenario. Based on this, we can determine the display priority standard. This allows for adjustments to existing preset rules instead of creating standards from scratch, improving processing efficiency and accuracy. Clarifying scenario relationships helps in making reasonable adjustments to the display priority standard later. Knowing the differences between the current scenario and the preset scenario allows for targeted modifications to the display priority, making the displayed content more in line with the needs of the actual scenario.

[0021] More specifically, even if the closest preset scenario is found, there are still some special circumstances or subtle differences in the actual scenario. Adaptively adjusting the display priority standard can ensure that the displayed content can accurately reflect the user's actual needs in the current scenario. For example, in some special congestion scenarios, there may be construction areas or special traffic control, requiring corresponding adjustments to the priority of the displayed content to provide users with more useful information. A reasonable display priority standard can make it easier and faster for users to obtain the most important information, reducing the time and effort users spend searching for information. By adaptively adjusting the display priority standard, we can better meet the needs of users in different scenarios, thereby improving the user experience.

[0022] Specifically, an in-vehicle vision module typically consists of devices such as cameras. It continuously captures and records the environment around the vehicle, such as road conditions, traffic signs, other vehicles, and pedestrians. In this step, these devices collect image or video data, which is the scene visual data. This data provides the raw data foundation for subsequent rendering processing. Only by first obtaining the actual scene information around the vehicle can content be rendered based on this information to ensure that the displayed content matches the actual situation, providing the driver with accurate visual information to assist them in making correct driving decisions.

[0023] More specifically, based on the display priority standard of the in-vehicle QD-MicroLED screen obtained above, a variety of different content rendering modes are designed. The display priority standard specifies the display priority of different information. Different rendering strategies can be adopted according to these priorities. For example, for high-priority information, larger fonts, brighter colors, and more prominent positions can be used for rendering; for low-priority information, smaller fonts, lighter colors, or rendering in a position that does not affect the display of the main information can be used.

[0024] More specifically, since different display priority standards require different rendering methods, and real-world scenarios involve a variety of variations, a single rendering mode cannot meet all needs. Generating multiple rendering modes can increase the diversity of choices, improve the likelihood of finding the most suitable rendering mode for the current scenario, and thus better meet the visual needs of users in different scenarios.

[0025] More specifically, for each generated content rendering mode, scene visual data is input for rendering processing, and the rendered result is presented. Then, the rendering effect is evaluated from multiple aspects, including information readability, visual comfort, and the prominence of key information. For example, for the rendering of traffic signs, their clarity and legibility are evaluated; for the rendering of the overall image, whether it will cause visual fatigue to the driver is evaluated. Through these evaluations, the effect parameters corresponding to each content rendering mode are obtained. By performing actual rendering processing and effect evaluation of each rendering mode, the advantages and disadvantages of each mode can be objectively understood. The effect parameters can quantitatively reflect the performance of each mode, providing a scientific basis for selecting the optimal mode, avoiding the selection of rendering modes based solely on subjective judgment, and improving the accuracy and reliability of the selection.

[0026] More specifically, based on the obtained effect parameters, all content rendering modes are compared, and the content rendering mode with the best effect parameters is selected. This optimal mode can maximize the effect of information transmission and the user's visual experience while meeting the display priority standard. It ensures that the scene visual data can be presented in the best way under the current vehicle operation scenario and display priority standard. The optimal mode can make important information more prominent and clear, improve the efficiency and quality of information transmission, reduce the time and effort for the driver to obtain key information, and improve driving safety and comfort.

[0027] More specifically, several preparatory modes are selected from content rendering modes that have relatively good but not optimal performance parameters. As the vehicle operation scene changes, the current optimal mode becomes inapplicable. Therefore, at certain intervals (e.g., every few minutes), these preparatory modes are re-analyzed using the current scene visual data. If a preparatory mode is found to perform better in the current scene, it can be selected to replace the current optimal mode. Considering that the vehicle operation scene is dynamically changing, the current optimal mode will become inapplicable as the scene changes. The existence of preparatory modes can quickly find a more suitable rendering mode when the scene changes, avoiding a lot of analysis and selection work when switching modes. This ensures that the rendering effect of the displayed content can always adapt to the constantly changing scene, improving the flexibility and adaptability of the system.

[0028] This application provides an adaptive display method for an in-vehicle QD-MicroLED screen, which has the following advantages: The aforementioned adaptive display method for in-vehicle QD-MicroLED screens analyzes sensor data to clearly define the operating scenario, enabling precise adaptation to display requirements. Based on this, the determined display priority standard prioritizes the presentation of important information, improving information acquisition efficiency. By generating the optimal rendering mode based on the standard, visual data can be rendered in different scenarios, optimizing display effects and ensuring visual comfort. It also reduces unnecessary information interference, allowing drivers to focus on road conditions and improving driving safety. At the same time, it fully leverages the advantages of QD-MicroLED screens to deliver a better interactive experience.

[0029] In one embodiment, the steps of acquiring raw monitoring data collected by the vehicle-mounted sensing module and analyzing the vehicle's environment based on the raw monitoring data to obtain vehicle operating environment information include: S11: By using the vehicle-mounted sensor module installed on the vehicle, multi-dimensional data monitoring of the vehicle is performed to obtain raw monitoring data containing several monitoring items. S12: Analyze the scene where the vehicle is located based on the original monitoring data to obtain several scene characteristics for feedback on the scene where the vehicle is located; S13: Combine the characteristics of each scenario to generate vehicle operation scenario information.

[0030] Specifically, vehicle-mounted sensing modules typically contain various types of sensors, each responsible for monitoring data in different dimensions. Speed ​​sensors are generally installed in the vehicle's transmission system and calculate the vehicle's speed by measuring the rotational speed of the wheels. They collect speed data at regular intervals (such as once per second) and transmit this data to the vehicle's central processing unit. Accelerometers can detect changes in vehicle acceleration in various directions. They are typically based on microelectromechanical systems (MEMS) technology and can sense the vehicle's acceleration, deceleration, and turning actions in real time, feeding back the corresponding acceleration values ​​to the system.

[0031] More specifically, temperature sensors are distributed in different parts of the vehicle, such as the engine compartment and the external environment. They use thermistors and other principles to measure temperature, converting the temperature value into an electrical signal and transmitting it to the data acquisition system. Humidity sensors are used to measure the humidity of the vehicle's surrounding environment. They generally use capacitive or resistive humidity sensing elements and convert humidity information into a processable electrical signal. Radar sensors are installed in the front and rear bumpers of the vehicle and detect the distance and relative speed between the vehicle and surrounding obstacles by emitting and receiving electromagnetic waves. They continuously scan the surrounding environment and send the detected target information (such as distance, angle, speed, etc.) to the vehicle control system. The data collected by these sensors is aggregated in the vehicle's central data processing unit to form raw monitoring data containing multiple monitoring items.

[0032] More specifically, vehicle operation is affected by a variety of factors, and single-dimensional data cannot accurately describe the actual situation of the vehicle. Through multi-dimensional data monitoring, information on the vehicle's own status (such as speed and acceleration) and the surrounding environment (such as temperature, humidity, and obstacle conditions) can be obtained, providing a rich and comprehensive data foundation for subsequent scenario analysis. Data from different sensors can corroborate and complement each other. For example, combining data from speed sensors and radar sensors can more accurately determine whether the vehicle is in normal driving, congestion, or a stopped state. The comprehensive use of multi-dimensional data can reduce scenario judgment errors caused by the error or limitation of a single sensor.

[0033] More specifically, each monitoring item in the raw monitoring data is analyzed individually. Based on preset rules and algorithms, the type of scene the vehicle is in is determined. For example, if the speed sensor shows that the vehicle speed is 0 and the radar sensor detects dense obstacles around the vehicle, combined with map information, it is determined that the vehicle is in a parking lot scene. Then, the code corresponding to "parking lot scene" is retrieved from the preset coding library, and the interaction correlation analysis of the codes of each scene type is performed. The association rule mining algorithm can be used to find the potential correlation between different codes. For example, there is a strong correlation between the "night scene" code and the "low light intensity scene" code. By analyzing these correlations, the scene in which the vehicle is in can be understood more comprehensively.

[0034] More specifically, based on the results of information association parsing, the information fed back by each scene type encoding is processed. Mutually exclusive content is removed to avoid information redundancy; associated content is expanded to make the scene description more complete. At the same time, a fusion weight is generated for each scene type encoding. The magnitude of the weight can be determined according to the importance of the encoding in describing the scene. For example, when judging whether a vehicle is in a dangerous scene, the weight of the encoding "the distance to the obstacle ahead is too close" will be set higher. The scene type encoding is combined with the corresponding fusion weight to form a scene feature, such as "parking lot scene (encoding: P01, weight: 0.8)" and "low light intensity scene (encoding: L02, weight: 0.6)".

[0035] More specifically, weighted summation or other comprehensive calculation methods are used to integrate the characteristics of each scenario. For example, the corresponding encoded information can be weighted according to the weight of each scenario characteristic, and then the processed results are summarized to obtain an information description that can comprehensively reflect the current operating scenario of the vehicle, such as "the vehicle is currently in a parking lot scenario with low light intensity".

[0036] More specifically, raw monitoring data is usually large and fragmented. Directly using this data for scenario judgment would be very complex and inefficient. By analyzing the raw data and extracting key characteristics that reflect the scenario in which the vehicle is located, the complex data can be simplified into information that is easy to process and understand, thereby improving the efficiency and accuracy of scenario analysis. The information association parsing and content adjustment process can take into account the interrelationships between different scenario types to avoid a one-sided understanding of the scenario. At the same time, generating fusion weights for scenario type encoding can highlight the importance of different scenario characteristics in describing the vehicle's operating scenario, making the final generated operating scenario information more consistent with the actual situation.

[0037] More specifically, a single scene characteristic can only reflect a certain aspect of the vehicle's operating scenario. Combining various scene characteristics can form a complete and comprehensive vehicle operating scenario information. Such information can provide an accurate basis for the subsequent adaptive display of the in-vehicle QD-MicroLED screen, enabling the displayed content to better adapt to the current operating scenario of the vehicle. Integrating scene characteristics into unified operating scenario information facilitates further processing and application of this information by the subsequent system. For example, the operating scenario information can be directly input into the scene display priority framework to quickly determine the display priority standard of the in-vehicle QD-MicroLED screen.

[0038] In one embodiment, the step of analyzing the vehicle's location based on the original monitoring data to obtain several scene characteristics for feedback on the vehicle's location includes: S121: Based on the monitoring items contained in the original monitoring data, the scene type of the vehicle is in is analyzed, and the scene type code of the corresponding analysis result is retrieved from the preset code library. S122: Perform interactive correlation analysis on each of the scene type codes to obtain the information correlation form between the information fed back by each of the scene type codes; S123: Based on the information association form, mutually exclusive content is removed and associated content is expanded for the feedback information of each scene type code, so as to retrieve several scene type codes with corresponding adjusted content from the preset coding library, and fusion weights are generated synchronously for each scene type code. S124: Combine the scene type code with the corresponding fusion weight to form a scene feature.

[0039] Specifically, the data of each monitoring item in the raw monitoring data is classified, and different types of monitoring item data correspond to different scene parsing rules. For example, for speed sensor data, if the speed remains at 0 for a long time, it is parsed as a parking scene; if the speed fluctuates within the speed limit range of urban roads, it is parsed as a normal urban driving scene. According to the preset scene parsing rules, each monitoring item data is matched with the rules. These rules can be summarized based on a large number of experiments and experience. For example, when the temperature sensor data shows that the temperature is below 0°C and the humidity sensor data shows that the humidity is high, combined with the weather data, it is parsed as a snowfall scene. Once the scene type is determined, the corresponding scene type code is retrieved from the preset code library. The preset code library is a pre-established database that stores various scene types and their corresponding codes. For example, the code "HW01" corresponds to the "highway driving scene".

[0040] More specifically, raw monitoring data is often complex and massive, making it very difficult to perform scene analysis directly. By parsing it into scene type codes, complex data can be simplified into easily processed and managed coding formats, improving the efficiency of subsequent analysis. The pre-set coding library provides a unified coding representation for different scene types, enabling different monitoring data to be compared and analyzed under the same standard. This helps improve the accuracy and consistency of scene analysis and avoids confusion and errors caused by different description methods.

[0041] More specifically, association rule mining algorithms, such as the Apriori algorithm or the FP-growth algorithm, are used to analyze all scene type codes. These algorithms can find frequent association patterns between different codes. For example, by analyzing a large amount of scene data, it is found that the codes for "night scene" and "low light intensity scene" often appear simultaneously, indicating that there is a strong association between them. Based on the mined association patterns, an association model between scene type codes is established. This association can be represented by a graph structure, where nodes represent scene type codes, edges represent the association between them, and the weight of the edges can represent the strength of the association. Based on the association model, the form of information association between the information fed back by each scene type code is determined, such as causal association, simultaneous association, conditional association, etc. For example, there is a causal association between the codes for "rainy day scene" and "slippery road scene".

[0042] More specifically, the vehicle's operating scenario is a complex system, with different scenario types interrelated and influencing each other. By analyzing the relationships between scenario type codes, we can gain a more comprehensive and in-depth understanding of the actual scenario in which the vehicle is located, avoiding a one-sided understanding of the scenario. Association rule mining can discover some potential information and patterns hidden in the data. The relationships between some scenario types are not obvious intuitively, but they can be revealed through data analysis. This helps to predict the situation the vehicle will face in advance and provides a more sufficient basis for subsequent decision-making.

[0043] More specifically, based on the information association format, the system checks whether there are mutually exclusive contents in the information fed back by each scene type code. If so, redundant or contradictory information is removed. For example, "daytime scene" code and "nighttime scene" code cannot coexist in the same scene description; one of them needs to be retained based on the actual situation. For scene type codes with related relationships, the information fed back is expanded. For example, if "rainy day scene" and "slippery road scene" are related, the information in the "rainy day scene" code can be supplemented with relevant descriptions of slippery roads. Based on the removed and expanded information, the corresponding adjusted scene type codes are retrieved from the preset code library. A fusion weight is generated for each adjusted scene type code. The weight generation can be based on various factors, such as the importance of the scene type in describing vehicle operation scenarios and its frequency of occurrence. Machine learning algorithms, such as decision tree algorithms or neural network algorithms, can be used to train a weight generation model based on historical data. The features of the current scene are then input into the model to obtain the fusion weight of each scene type code.

[0044] More specifically, eliminating mutually exclusive content can avoid information redundancy and contradictions, making the scene description more concise and accurate. Expanding related content can enrich the information in the scene description, making the portrayal of vehicle operation scenarios more comprehensive. Generating fusion weights for scene type encoding can highlight the importance of different scene types in describing vehicle operation scenarios. In the subsequent process of scene characteristic combination and operation scenario information generation, scene type encoding with higher weights will have a greater impact on the final result, thus making the generated operation scenario information more reflective of the actual situation.

[0045] More specifically, each scene type code is combined with its corresponding fusion weight to form a tuple, for example, ("Rainy Day Scene (Code: R01)", 0.8), where 0.8 is the fusion weight of the scene type code. These tuples are used as a scene feature to describe a certain aspect of the scene in which the vehicle is located. Combining multiple scene features can more comprehensively describe the vehicle's operating scene.

[0046] More specifically, scene type encoding and fusion weights are combined to form scene features, providing basic feature units for constructing complete vehicle operation scene information. Each scene feature describes the characteristics of the scene in which the vehicle is located from different perspectives. The combination of multiple scene features can comprehensively and accurately depict the vehicle's operation scene. The form of scene features facilitates further processing and application by the subsequent system. For example, multiple scene features can be weighted and summed to obtain a comprehensive operation scene score, which can be used to assess the complexity or danger level of the scene in which the vehicle is located. Scene features can also be directly input into other related algorithms or models to support functions such as adaptive display of in-vehicle QD-MicroLED screens.

[0047] In one embodiment, the step of analyzing the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the operating scene information to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen includes: S21: Retrieve the scene display priority framework pre-deployed locally in the vehicle; S22: Substitute the running scene information into the scene display priority framework to analyze and obtain the scene association relationship of the running scene information relative to various preset running scenes of the scene display priority framework; S23: Based on the scene association relationship, retrieve the display priority standard of the preset running scene that is closest to the running scene information from the scene display priority framework, and make adaptive adjustments to the display priority standard to obtain the display priority standard of the vehicle QD-MicroLED screen.

[0048] Specifically, the vehicle's control system accesses a pre-deployed scene display priority framework in local storage devices (such as hard drives, flash memory, etc.) through a file system or database interface. This framework is usually stored in a specific data structure (such as tables, tree structures, etc.) for easy retrieval and reading. The data of the scene display priority framework is loaded into the vehicle's memory for subsequent analysis and processing. The loading process involves data decoding and parsing to ensure that the data can be correctly identified and used by the system.

[0049] More specifically, pre-deploying the scene display priority framework locally on the vehicle avoids retrieving data from a remote server when it is necessary to determine the display priority standard, thereby greatly shortening the processing time and improving the system's response speed. During vehicle operation, scene changes may be very rapid, and quickly determining the display priority standard is crucial for providing the driver with accurate information in a timely manner. The locally stored scene display priority framework is not affected by the network connection status. Even in the case of poor network signal or no network, the vehicle can still retrieve the framework normally, ensuring the normal operation of the system.

[0050] More specifically, key features in the running scene information (such as scene type, environmental parameters, etc.) are matched one by one with the features of various preset running scenes in the scene display priority framework. Similarity calculation methods, such as Euclidean distance and cosine similarity, can be used to measure the degree of similarity between the running scene information and the preset running scenes. Based on the feature matching results, the correlation between the running scene information and various preset running scenes is analyzed. For example, if the similarity between the running scene information and a certain preset running scene exceeds a set threshold, it is considered that there is a strong correlation between them; if the similarity is low, the correlation is weak. All preset running scenes are sorted according to their correlation with the running scene information so that the closest preset running scene can be selected later.

[0051] More specifically, actual vehicle operating scenarios are highly variable, making it difficult to find a perfect match within preset operating scenarios. By analyzing scenario relationships, we can identify the preset operating scenario that is closest to the current operating scenario. Based on this, we can determine the display priority standard. This allows us to utilize pre-defined standards, reducing the workload of re-establishing standards, improving processing efficiency, and clarifying the relationship between operating scenario information and preset operating scenarios. This helps in making reasonable adjustments to the display priority standard later. Knowing the differences between the current scenario and the preset scenario allows us to modify the display priority in a targeted manner, making the displayed content more in line with the needs of the actual scenario.

[0052] More specifically, a preset operating scenario with the highest relevance to the operating scenario information is selected from the scenario display priority framework, and the display priority standard corresponding to the preset operating scenario is retrieved. The display priority standard usually specifies the display priority order of different display content (such as navigation information, vehicle status information, entertainment information, etc.). Although the selected preset operating scenario is closest to the current operating scenario, there may still be some differences. Therefore, it is necessary to make adaptive adjustments to the retrieved display priority standard. The basis for adjustment can be the characteristics in the operating scenario information that are different from the preset operating scenario. For example, if there is special traffic control in the current operating scenario, but the preset operating scenario does not take this into account, then it is necessary to increase the display priority of traffic control related information.

[0053] More specifically, rule engines or machine learning models can be used for adaptive adjustments. Rule engines modify the display priority criteria according to preset rules, while machine learning models predict how to adjust the display priority criteria in the current operating scenario by learning from historical data.

[0054] More specifically, the display priority standard for preset operating scenarios in the scene display priority framework is derived from extensive experiments and data analysis, possessing a certain degree of scientific validity and rationality. By retrieving the display priority standard of the closest preset operating scenario, we can fully utilize these existing experiences and ensure the basic rationality of the display priority standard. Since actual operating scenarios may differ from preset operating scenarios, directly using the preset display priority standard may not meet the needs of the current scenario. By adaptively adjusting the display priority standard, the displayed content can better adapt to the current actual operating scenario of the vehicle, improving the efficiency and accuracy of the driver's information acquisition, thereby enhancing driving safety and comfort.

[0055] In one embodiment, the pre-construction steps of the scenario display priority framework include: S201: Obtain visual capture performance data from the vehicle-mounted vision module; S202: Combine the visual capture performance data with various preset operating scenarios to simulate the expected visual data of the vehicle vision module under each preset operating scenario, and obtain the expected visual dataset corresponding to each preset operating scenario. S203: Based on the preset operating scenario, predict and analyze the reading needs of vehicle users for the in-vehicle QD-MicroLED screen to obtain predictive information on the reading needs of vehicle users for the in-vehicle QD-MicroLED screen. S204: Based on the reading demand prediction information, analyze the reading demand of the expected visual dataset to obtain priority labeling information; S205: Interpret the priority labeling information according to the priority display rules to obtain the display priority standard; S206: Combine the display priority standards of the vehicle vision module relative to various preset operating scenarios to obtain a scene display priority framework.

[0056] Specifically, basic hardware parameters such as camera resolution (e.g., 1920×1080 pixels), frame rate (e.g., 30 frames / second), sensitivity (e.g., ISO 100-3200), and field of view (120° horizontal and 60° vertical) are obtained directly from the technical documentation or hardware equipment of the vehicle vision module. The vehicle vision module is then tested in a laboratory or actual road environment. By inputting different types of image or video samples, the module's image capture performance under different brightness, contrast, and color conditions is recorded to evaluate its imaging quality and capture capability in different scenarios and obtain more accurate visual capture performance data.

[0057] More specifically, the visual capture performance of the vehicle vision module directly affects the quality of the visual data it collects in different scenarios. Obtaining accurate performance data is the foundation for subsequent simulation of expected visual data. Only by simulating based on real performance parameters can we obtain an expected visual dataset that is close to the actual situation, providing reliable data support for determining display priority standards.

[0058] More specifically, based on common vehicle operating conditions, various preset operating scenarios are defined, such as urban road driving, highway driving, parking lot parking, night driving, and rainy driving. Based on computer graphics and image processing technology, simulation models are established, and visual capture performance data is used as input parameters of the models. Combined with the characteristics of the preset operating scenarios (such as the lighting conditions and object distribution of the scenarios), the images or videos captured by the vehicle vision module under different preset operating scenarios are simulated. Each preset operating scenario is simulated multiple times to generate a large amount of expected visual data, forming the expected visual dataset corresponding to each preset operating scenario.

[0059] More specifically, actual vehicle operating scenarios are complex and diverse, making it difficult to cover all situations in actual testing. Through simulation, a large amount of expected visual data can be generated under different preset operating scenarios, comprehensively covering all possible scenarios. This provides rich data samples for subsequent analysis of user reading needs and determination of display priority standards. Before the vehicle is actually running, by simulating the expected visual dataset, the display content under different scenarios can be planned and analyzed in advance, avoiding situations where the display content is unreasonable or fails to meet user needs during actual use.

[0060] More specifically, through questionnaires, interviews, and other methods, a large number of vehicle users' needs and preferences for the content displayed on the in-vehicle QD-MicroLED screen under different preset operating scenarios were collected. For example, when driving on urban roads, users pay more attention to navigation information and traffic sign prompts; when parking in a parking lot, users need to check the surrounding parking space information. Using data analysis technology and machine learning algorithms, the collected user survey data was analyzed and modeled. Based on the characteristics of the preset operating scenarios, the degree of reading needs of vehicle users for different display content on the in-vehicle QD-MicroLED screen under the scenario was predicted, and reading demand prediction information was obtained.

[0061] More specifically, the content displayed on in-vehicle QD-MicroLED screens ultimately serves vehicle users. Understanding users' reading needs under different preset operating scenarios is key to determining display priority standards. Through predictive analytics, user needs and preferences can be understood in advance, making the displayed content more in line with the user's actual usage and improving the user experience.

[0062] More specifically, the content to be displayed in the expected visual dataset is categorized, such as navigation information, vehicle status information (speed, fuel level, etc.), entertainment information, and warning information. Information is predicted based on reading needs, and a priority is assigned to each category of content. For example, in a highway driving scenario, navigation information and vehicle status information have higher priority, while entertainment information has lower priority. The annotation results are recorded to form priority annotation information.

[0063] More specifically, by translating users' reading needs into specific priority labeling information, the needs become more quantifiable and clear. This helps in the subsequent sorting and management of displayed content, ensuring that the information most needed by users is displayed first within the limited screen space.

[0064] More specifically, the priority labeling information is analyzed in depth to uncover the priority display patterns. Through statistical analysis and association rule mining, the changing patterns and influencing factors of displayed content priority under different preset operating scenarios are identified. Based on the uncovered patterns, display priority standards are formulated, which clearly stipulate the display priority order of various types of displayed content under different preset operating scenarios, and how to select displayed content when resources are limited.

[0065] More specifically, by interpreting the patterns in priority labeling information, we can identify the inherent patterns in the priority of displayed content in different scenarios, providing a basis for formulating scientific and reasonable display priority standards. The standards formulated in this way are systematic and logical, and can better adapt to changes in various preset operating scenarios.

[0066] More specifically, the display priority standards for each preset running scenario will be integrated to form a unified dataset, and the structure of the scenario display priority framework will be built. The integrated display priority standards will be organized and stored according to the classification of preset running scenarios to facilitate subsequent querying and retrieval.

[0067] More specifically, the display priority standards for different preset operating scenarios are combined into a scenario display priority framework, which facilitates unified management and application of the entire system. During actual vehicle operation, the corresponding display priority standard can be quickly retrieved from the framework according to the current operating scenario to achieve adaptive adjustment of the displayed content.

[0068] In one embodiment, the steps of acquiring scene visual data collected by the vehicle-mounted vision module, performing an adaptive analysis of the content rendering mode on the scene visual data according to the display priority criterion, and generating the optimal content rendering mode include: S31: Visual data of the scene around the vehicle is obtained by visually acquiring the scene through the vehicle-mounted vision module installed on the vehicle. S32: Generate several corresponding content rendering modes according to the display priority criteria, and perform rendering processing and effect evaluation on the scene visual data based on each of the content rendering modes to obtain the effect parameters of each content rendering mode, so as to select the optimal content rendering mode.

[0069] Specifically, an in-vehicle vision module typically consists of multiple cameras distributed in different locations on the vehicle, such as the front, rear, and sides. These cameras continuously capture images of the surrounding environment at a certain frame rate (e.g., 30 or 60 frames per second), converting optical images into electrical signals. After analog-to-digital conversion and other processing, these signals are transformed into digital images or video data. The acquired scene visual data is transmitted to the vehicle's central processing unit or a dedicated data processing module via the vehicle's internal data transmission bus (e.g., CAN bus, Ethernet). During transmission, the data may be compressed or encoded to reduce transmission bandwidth and storage requirements. The processed data is temporarily stored in memory or hard drives for subsequent analysis and processing.

[0070] More specifically, scene visual data is a direct reflection of the actual environment around the vehicle and is the foundation for subsequent content rendering and display. Only by acquiring accurate and real-time scene visual data can the actual situation around the vehicle be displayed in a suitable way on the in-vehicle QD-MicroLED screen, providing useful information for the driver. Different scenes require different rendering methods. By continuously collecting scene visual data, changes in the scene can be captured in a timely manner, thereby dynamically adjusting the content rendering mode according to the actual scene and achieving adaptive rendering of the displayed content.

[0071] More specifically, based on the priority order and display requirements of different content in the display priority standard, various rendering rules are designed. For example, for high-priority information, larger fonts, brighter colors, and more prominent positions can be used for rendering; for low-priority information, smaller fonts, lighter colors, or rendering in areas that do not affect the display of the main information can be used. In addition to priority, other factors such as the size, resolution, and color mode of the display screen are also considered. Several specific content rendering modes are generated by combining these factors. For example, different icon sizes and layouts are designed for screens with different resolutions.

[0072] More specifically, the most important scene information differs depending on the operating scenario. The most suitable rendering mode is selected based on the different operating scenarios to display the most important scene information, so that users can clearly obtain the most important scene information in the current operating scenario.

[0073] More specifically, the scene visual data collected from the storage device is loaded and input into the rendering engine corresponding to each content rendering mode. The rendering engine processes the scene visual data according to the rules of each rendering mode to generate rendered images or videos. During the rendering process, operations such as image scaling, cropping, color adjustment, and text overlay may be involved.

[0074] More specifically, a series of metrics for evaluating rendering effects are determined, such as information readability (by calculating text clarity, contrast, etc.), visual comfort (by analyzing color matching, brightness distribution, etc.), and the prominence of key information (by detecting the visual salience of high-priority information). Specialized evaluation tools or algorithms are used to quantitatively evaluate the rendering results under each rendering mode, obtain the numerical value corresponding to each evaluation metric, and combine these values ​​into the effect parameters of that rendering mode.

[0075] More specifically, the performance parameters of all content rendering modes are compared. Different weights can be assigned to different evaluation metrics based on their importance, and then a comprehensive score is calculated for each rendering mode. The rendering mode with the highest comprehensive score is selected as the optimal content rendering mode.

[0076] More specifically, the display priority standard only specifies the display priority of content, but the specific display effect can be achieved through a variety of different rendering modes. Generating multiple rendering modes can meet the diverse display needs in different scenarios, improve the flexibility and adaptability of the display effect, and by evaluating and comparing the effects of each rendering mode, the optimal content rendering mode can be selected to ensure that, under the current display priority standard and scene visual data, the in-vehicle QD-MicroLED screen can present scene information in the best way, improve the readability of information and the user's visual experience, and ensure driving safety and comfort.

[0077] In one embodiment, the method further includes: selecting several preparatory modes from several non-optimal content rendering modes based on the effect parameters, and performing an adaptive analysis of the content rendering modes on each of the preparatory modes using the scene visual data at predetermined intervals, so as to determine whether to select a preparatory mode to replace the current optimal content rendering mode.

[0078] Specifically, all content rendering modes are sorted according to their performance parameters (such as overall score), with the optimal rendering mode at the top. From the non-optimal rendering modes, several are selected as reserve modes according to preset rules. This can be a certain number (e.g., 2-3) of rendering modes with high performance parameter rankings, or rendering modes whose performance parameters differ from the optimal mode within a certain range. When selecting reserve modes, in addition to performance parameters, the diversity of rendering modes is also considered. This ensures that the reserve modes differ from the optimal mode in rendering style, how they handle different types of information, etc., to cope with possible scene changes.

[0079] More specifically, a predetermined time interval (such as 1 minute or 5 minutes) is set. When the time is up, the system automatically triggers the adaptive analysis process for the preparatory modes, inputs the currently collected scene visual data into the rendering engine corresponding to each preparatory mode for rendering processing, evaluates the rendering results of each preparatory mode according to the evaluation metrics and methods used when evaluating the optimal mode, obtains new effect parameters, and compares and analyzes the new effect parameters of each preparatory mode with the effect parameters of the current optimal mode. The difference between the two can be calculated to evaluate whether the performance of the preparatory mode in the current scene is better than or close to the current optimal mode.

[0080] More specifically, some judgment thresholds are set. If the difference between the overall score of a certain preparatory mode and the overall score of the current optimal mode is less than a certain threshold, and the preparatory mode performs better in some key evaluation indicators (such as the degree of emphasis of key information), then the preparatory mode can be considered to have the potential to replace the current optimal mode. Based on the results of comparative analysis and threshold judgment, if a certain preparatory mode is considered to be more suitable for the current scenario, it is selected as the new optimal content rendering mode and replaces the current optimal mode; if all preparatory modes do not meet the replacement conditions, the current optimal mode remains unchanged.

[0081] More specifically, the vehicle's operating environment is dynamic and changing. The current optimal rendering mode may no longer be applicable after the scene changes. Selecting several backup modes can reserve different rendering strategies in advance so that a more suitable rendering mode can be quickly found when the scene changes, avoiding poor display effects due to scene changes. Backup modes are diverse and may show better adaptability in different scenarios. By reserving multiple backup modes, the flexibility of system selection can be increased, and the system's adaptability to various complex scenarios can be improved.

[0082] More specifically, regularly performing adaptive analysis on the pre-set mode can promptly identify changes in the scene and whether the current optimal mode is still applicable. Over time, the environment around the vehicle, traffic conditions, and other factors may change. By regularly analyzing the pre-set mode, it can be ensured that the displayed content is always presented in the optimal way. Setting a predetermined time interval for analysis can avoid switching rendering modes too frequently, reduce the system's processing burden and display instability, and at the same time, it can respond promptly when the scene changes significantly, ensuring the continuity and stability of the display effect.

[0083] More specifically, by comparing the effect parameters of the preparatory mode and the current optimal mode, it can be determined whether to select the preparatory mode to replace the current optimal mode. This ensures that the in-vehicle QD-MicroLED screen always displays scene information in the best rendering mode. When the scene changes, timely switching to a more suitable rendering mode can improve the readability of information and the user's visual experience, and ensure driving safety. Using threshold judgment and other methods for decision-making makes the mode replacement process more scientific and objective, avoiding the problem of unstable or poor display effects caused by subjective judgment or random selection, and improving the reliability and stability of the system.

[0084] In one embodiment, such as Figure 2 As shown, an adaptive display system for an in-vehicle QD-MicroLED screen is provided, used to implement the adaptive display method for an in-vehicle QD-MicroLED screen as described in any one of the first aspects, comprising: The scene monitoring module is used to acquire the raw monitoring data collected by the vehicle-mounted sensing module and analyze the scene in which the vehicle is located based on the raw monitoring data to obtain the vehicle's operating scene information. The priority analysis module is used to analyze the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the operation scene information, so as to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen. The mode selection module is used to acquire scene visual data collected by the vehicle vision module, and perform an adaptive analysis of the content rendering mode on the scene visual data according to the display priority standard to generate the optimal content rendering mode for subsequent scene visual data content rendering.

[0085] In this embodiment, the specific implementation of each module in the above system embodiment is described in the above method embodiment, and will not be repeated here.

[0086] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0087] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0088] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0089] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An adaptive display method for an in-vehicle QD-MicroLED screen, characterized in that, include: The system acquires raw monitoring data collected by the vehicle-mounted sensor module and analyzes the vehicle's location based on the raw monitoring data to obtain vehicle operation scenario information. Based on the aforementioned operating scenario information, the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen is analyzed to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen. The system acquires scene visual data collected by the vehicle-mounted vision module, performs an adaptive analysis of the content rendering mode on the scene visual data according to the display priority standard, and generates the optimal content rendering mode for subsequent scene visual data content rendering.

2. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 1, characterized in that, The steps of acquiring raw monitoring data collected by the vehicle-mounted sensor module and analyzing the vehicle's operating scene based on the raw monitoring data to obtain vehicle operating scene information include: By installing on-board sensor modules on the vehicle, multi-dimensional data monitoring of the vehicle is carried out to obtain raw monitoring data containing several monitoring items. The vehicle's location is analyzed based on the original monitoring data to obtain several scene characteristics used to provide feedback on the vehicle's location. The characteristics of each scenario are combined to generate vehicle operation scenario information.

3. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 2, characterized in that, The steps of analyzing the vehicle's location based on the original monitoring data to obtain several scene characteristics for feedback on the vehicle's location include: Based on the monitoring items contained in the original monitoring data, the scene type of the vehicle's location is analyzed, and the scene type code of the corresponding analysis result is retrieved from the preset coding library. The interaction correlation of each scene type code is analyzed to obtain the information correlation form between the information fed back by each scene type code; Based on the aforementioned information association format, mutually exclusive content is removed and associated content is expanded from the feedback information of each scene type code, so as to retrieve several scene type codes with corresponding adjusted content from the preset coding library, and to generate fusion weights for each scene type code simultaneously. The scene type code is combined with the corresponding fusion weight to form a scene feature.

4. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 1, characterized in that, The steps for analyzing the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the aforementioned operating scene information to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen include: Retrieve the scene display priority framework pre-deployed locally on the vehicle; The running scenario information is substituted into the scenario display priority framework to analyze and obtain the scenario association relationship between the running scenario information and various preset running scenarios of the scenario display priority framework; Based on the scene association, the display priority standard of the preset running scene that is closest to the running scene information is retrieved from the scene display priority framework, and the display priority standard is adaptively adjusted to obtain the display priority standard of the vehicle QD-MicroLED screen.

5. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 4, characterized in that, The pre-construction steps of the scene display priority framework include: Acquire visual capture performance data from the vehicle-mounted vision module; The visual capture performance data is combined with various preset operating scenarios to simulate the expected visual data of the vehicle vision module under each preset operating scenario, thereby obtaining the expected visual dataset for each preset operating scenario. Based on preset operating scenarios, predictive analysis is performed on the reading needs of vehicle users for in-vehicle QD-MicroLED screens to obtain predictive information on the reading needs of vehicle users for in-vehicle QD-MicroLED screens. Based on the reading demand prediction information, the expected visual dataset is analyzed to obtain priority labeling information; The priority labeling information is interpreted to determine the priority display rules, thereby obtaining the display priority standard; The vehicle vision module is combined with the display priority criteria of various preset operating scenarios to obtain a scene display priority framework.

6. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 1, characterized in that, The steps of acquiring scene visual data collected by the vehicle-mounted vision module, performing adaptive analysis of the scene visual data on the content rendering mode according to the display priority criteria, and generating the optimal content rendering mode include: Visual data of the scene is obtained by visually capturing the surrounding environment of the vehicle through an onboard vision module installed on the vehicle. Several corresponding content rendering modes are generated based on the display priority criteria. The scene visual data is then rendered and the effect is evaluated based on each of the content rendering modes to obtain the effect parameters of each content rendering mode, so as to select the optimal content rendering mode.

7. The adaptive display method for an in-vehicle QD-MicroLED screen as described in claim 6, characterized in that, Also includes: Based on the effect parameters, several reserve modes are selected from several non-optimal content rendering modes, and the scene visual data is used at predetermined intervals to perform an adaptive analysis of the content rendering mode for each reserve mode in order to determine whether to select a reserve mode to replace the current optimal content rendering mode.

8. An adaptive display system for an in-vehicle QD-MicroLED screen, characterized in that, An adaptive display method for an in-vehicle QD-MicroLED screen according to any one of claims 1-7 includes: The scene monitoring module is used to acquire the raw monitoring data collected by the vehicle-mounted sensing module and analyze the scene in which the vehicle is located based on the raw monitoring data to obtain the vehicle's operating scene information. The priority analysis module is used to analyze the display priority of the scene display content of the vehicle-mounted QD-MicroLED screen based on the operation scene information, so as to obtain the display priority standard of the vehicle-mounted QD-MicroLED screen. The mode selection module is used to acquire scene visual data collected by the vehicle vision module, and perform an adaptive analysis of the content rendering mode on the scene visual data according to the display priority standard to generate the optimal content rendering mode for subsequent scene visual data content rendering.

Images