A dynamic HMI color optimization method and system based on scene switching

Abstract

The application relates to the technical field of human-computer interaction, and provides a dynamic HMI color optimization method and system based on scene switching, which introduces environment information, state information and display information based on a machine learning model, calculates a comprehensive optimization coefficient of a current interface corresponding to a current scene, and then dynamically adjusts the interface display attributes (brightness, contrast and color temperature) of the corresponding scene according to the comprehensive optimization coefficient, realizes adaptive color optimization through multivariable weighting, accurately optimizes HMI display parameters through comprehensive real-time data, improves the display effect, and thus improves driving safety and information recognition efficiency, and further improves user experience and visual comfort; meanwhile, the comprehensive optimization coefficient is adjusted according to the obtained user operation feedback, preset display attributes under different scene interfaces are further optimized, personalized user experience can be enhanced, and the risk of user distraction operation is reduced.

Description

Technical Field

[0001] This invention relates to the field of human-computer interaction technology, and in particular to a dynamic HMI color optimization method and system based on scene switching. Background Technology

[0002] HMI display optimization refers to improving the visual design, interaction logic, and information presentation of the Human-Machine Interface (HMI) to enhance operational efficiency, reduce cognitive load, and improve user experience and safety. Its core objective is to enable users (such as operators and drivers) to obtain key information and complete interactive tasks more intuitively and efficiently.

[0003] With the widespread use of smart devices, traditional HMI display optimization technologies typically rely on adjusting a single factor (such as ambient light intensity). While simple and easy to implement, this approach has significant limitations and struggles to meet the needs of complex scenarios. Consequently, it is difficult to achieve accurate optimization in complex environments, and it may even become disconnected from the system state, affecting the transmission of critical information and reducing interface readability or visual comfort, thereby impacting user experience, security, and operational efficiency. Summary of the Invention

[0004] This invention provides a dynamic HMI color optimization method and system based on scene switching, which solves the technical problem in existing HMI display optimization technology that the influencing factors are not fully considered, making it unable to adapt to complex scenes, resulting in difficulty in obtaining interface information and poor user experience.

[0005] To address the above technical problems, this invention provides a dynamic HMI color optimization method based on scene switching, comprising: Real-time collection of environmental information of the current scene and acquisition of vehicle status information; Identify the interface elements of the current interface, analyze the complexity of the current interface based on the interface elements, and use this as display information; Based on a machine learning model, the comprehensive optimization coefficient of the current interface corresponding to the current scene is calculated according to the environmental information, state information and display information. The interface display attributes for the corresponding scenario are dynamically adjusted based on the comprehensive optimization coefficients. Based on the user operation feedback obtained, the comprehensive optimization coefficient is adjusted to further optimize the preset display attributes under different scenario interfaces.

[0006] This basic solution is based on a machine learning model, incorporating environmental, state, and display information to calculate the comprehensive optimization coefficient of the current interface for the current scenario. This comprehensive optimization coefficient then dynamically adjusts the interface display attributes (brightness, contrast, and color temperature) for the corresponding scenario. Adaptive color optimization is achieved through multi-variable weighting, and HMI display parameters are precisely optimized using comprehensive real-time data to improve display quality, thereby enhancing driving safety and information recognition efficiency, and ultimately improving user experience and visual comfort. Simultaneously, based on user operation feedback, the comprehensive optimization coefficient is adjusted to further optimize the preset display attributes under different scenario interfaces, enhancing personalized user experience and reducing the risk of user distraction.

[0007] In a further implementation plan, environmental information for different scenarios is collected in real time, and vehicle status information is obtained, including: An environmental perception sensor is used to acquire and collect real-time illumination data of the current scene as environmental information. Vehicle speed sensors are used to monitor vehicle speed in real time and obtain vehicle status information.

[0008] This solution uses environmental perception sensors and vehicle speed sensors to collect real-time data as the basis for adjusting the color of the driver interface, enabling precise adaptation to dynamic lighting environments and safety optimization linked to vehicle speed.

[0009] In a further implementation, the interface elements of the current interface are identified, and the complexity of the current interface is analyzed based on the interface elements as display information, including: Identify the element types, element quantities, and interface layout of the current interface elements, where the element types include the number of text elements and the number of images. Based on the element types, element quantities, and interface layout of the interface elements, the complexity of the current interface is calculated to obtain the display information.

[0010] This solution calculates interface complexity based on the types and quantities of interface elements and the interface layout, and uses this as the basis for interface color optimization. By dynamically balancing information density and visual comfort, it significantly improves the safety and efficiency of interaction in complex driving scenarios.

[0011] In a further implementation scheme, based on a machine learning model, the comprehensive optimization coefficient of the current interface is calculated according to the environmental information, state information, and display information, including: The current scene type is determined based on the environmental information and status information, and the preset weight parameters of each target display attribute under the corresponding scene type are obtained. Based on the dynamic adjustment algorithm, a first weight coefficient is calculated according to the environmental information and the corresponding preset weight parameters, a second weight coefficient is calculated according to the state information and the corresponding preset weight parameters, and a third weight coefficient is calculated according to the display information and the corresponding preset weight parameters. Calculate the attribute scores for each target display attribute for the environmental information, status information, and display information respectively; Integrate the first weight coefficient, the second weight coefficient, the third weight coefficient, and the corresponding attribute scores to calculate the comprehensive optimization coefficient of each target display attribute in the current scene; the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1.

[0012] This solution calculates weight coefficients for each target display attribute under corresponding scene types by using preset weight parameters. Based on real-time and preset scenes, it achieves integrated control between scene coefficients and dynamic adjustments, thereby simplifying optimization difficulty, improving optimization responsiveness, and enhancing the adaptability of automatic color adjustment during scene switching while performing precise color optimization. On the other hand, it integrates the first, second, and third weight coefficients and their corresponding attribute scores to calculate the comprehensive optimization coefficient for each target display attribute in the current scene. This accurately determines the attribute scores of different scene factors (environmental information, status information, and display information) on the user's interface, and then independently performs comprehensive automatic optimization of target display attributes, effectively improving user satisfaction.

[0013] In a further implementation scheme, the dynamic adjustment algorithm specifically includes: Based on the collected data and preset weight parameters, the adjustment direction and the actual difference are determined. The actual difference is converted into an adjustment amplitude according to a preset proportional coefficient. The target weight corresponding to the collected data is calculated based on the adjustment direction and the adjustment amplitude. The collected data includes environmental information, status information, and display information.

[0014] When making dynamic adjustments, this solution compares the collected data with the preset weight parameters to determine the adjustment direction and the actual difference. The actual difference is then converted into an adjustment amplitude according to a preset proportional coefficient. Based on the adjustment direction and adjustment amplitude, the target weight corresponding to the collected data is calculated. By combining real-time collected data, the solution makes proportional real-time dynamic adjustments to fully meet the needs of scene switching.

[0015] In a further embodiment, the target display attributes in the interface display attributes include brightness, contrast, and color temperature; The comprehensive optimization coefficient is calculated using a weighted average fusion algorithm, and its calculation formula is as follows:

[0016] In the formula, To comprehensively optimize the coefficients, , , These represent the first weighting coefficient, the second weighting coefficient, and the third weighting coefficient, respectively. , , These represent the attribute scores of the target display attributes for the environmental information, state information, and display information, respectively, while α, β, and γ represent the dynamic adjustment factors for the corresponding environmental information, state information, and display information under different scenarios.

[0017] When calculating the comprehensive optimization coefficient, this solution uses a weighted average fusion algorithm to integrate environmental, status, and display information for color optimization, achieving multi-dimensional error compensation. Real-time collected data is converted into attribute scores for corresponding target display attributes, and adaptive adjustments are made based on the impact of actual scene factors on different target display attributes. At the same time, dynamic adjustment factors for corresponding environmental, status, and display information under different scenarios are incorporated to systematically evaluate the actual performance of each attribute of the interface and provide precise optimization strategies for different scenarios.

[0018] In a further implementation scheme, the interface display attributes of the corresponding scene are dynamically adjusted according to the comprehensive optimization coefficient. Specifically, the comprehensive optimization coefficient corresponding to each target display attribute is obtained, the target display parameters are calculated based on the comprehensive optimization coefficient and the current display parameters, and a smooth transition adjustment is performed according to a preset step size.

[0019] This solution achieves a seamless and advanced experience in adjusting display attributes by using a preset step size for intelligent and smooth transition, while ensuring driving safety.

[0020] In a further implementation scheme, based on the obtained user operation feedback, the comprehensive optimization coefficient is adjusted to further optimize the preset display parameters under different scenario interfaces, including: Read user preferences; Obtain user feedback after adjusting the interface display parameters; Based on the user operation feedback, the change parameters of the corresponding target display attributes are determined, and the preset weight parameters are adjusted based on the change parameters and user preferences. The comprehensive optimization coefficient is then updated to further optimize the preset display parameters under different scenario interfaces.

[0021] This solution dynamically adjusts the comprehensive optimization coefficients and preset display parameters based on user feedback, which can significantly improve the personalized adaptability and scene optimization accuracy of the intelligent interactive interface.

[0022] This invention also provides a dynamic HMI color optimization system based on scene switching, used to implement the dynamic HMI color optimization method based on scene switching as described above: it includes a data acquisition module, a scene recognition module, a main control module, an execution module, and a personalization module; the data acquisition module is connected to the scene recognition module and the main control module, and the main control module is connected to the execution module and the personalization module; The data acquisition module is used to collect environmental information of the current scene in real time, obtain vehicle status information, and identify interface elements of the current interface. The scene recognition module is used to determine the scene type of the current scene based on the environmental information and status information; The main control module is used to analyze the complexity of the current interface based on the interface elements and use it as display information; it is also used to calculate the comprehensive optimization coefficient of the current interface corresponding to the current scene based on the environment information, state information and display information using a machine learning model. The execution module is used to dynamically adjust the interface display attributes of the corresponding scenario according to the comprehensive optimization coefficient; The personalization module is used to adjust the comprehensive optimization coefficient based on the obtained user operation feedback, and further optimize the preset display attributes under different scenario interfaces.

[0023] In a further embodiment, the data acquisition module includes an environmental perception sensor and a vehicle speed sensor; the environmental perception sensor includes at least one of a light sensor and a color temperature sensor.

[0024] The modules in this solution system are used to implement a dynamic HMI color optimization method based on scene switching, as described above. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the workflow of a dynamic HMI color optimization method based on scene switching, provided in an embodiment of the present invention. Figure 2 This is a system framework diagram of a dynamic HMI color optimization system based on scene switching provided in an embodiment of the present invention. Detailed Implementation

[0026] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. The embodiments are given for illustrative purposes only and should not be construed as limiting the present invention. The accompanying drawings are for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0027] Example 1 This invention provides a dynamic HMI color optimization method based on scene switching, such as... Figure 1 As shown, in this embodiment, it includes: S1. Collect scene data, including: S11. Real-time collection of environmental information for the current scene, specifically: An environmental perception sensor is used to acquire and collect real-time illumination data of the current scene as environmental information.

[0028] For example, high-precision photosensitive sensors such as photoresistors, photodiodes, and color temperature sensors can be used to acquire light and color temperature data in real time, with a sampling frequency of several times per second.

[0029] S12. Obtain vehicle status information, specifically: Vehicle speed sensors are used to monitor vehicle speed in real time and obtain vehicle status information.

[0030] For example, vehicle speed sensors (such as WSS or VSS) can be used to monitor vehicle speed in real time, with the sampling frequency synchronized with the vehicle control system.

[0031] This embodiment uses environmental perception sensors and vehicle speed sensors to collect real-time data as the basis for adjusting the color of the driver interface, which can realize the safety optimization of precise adaptation to dynamic light environment and linkage with vehicle speed.

[0032] S13. Identify the interface elements of the current interface, analyze the complexity of the current interface based on the interface elements, and use this as display information, including: Identify the element types, element quantities, and interface layout of the current interface elements, where the element types include the number of text elements and the number of images. Based on the element types, element quantities, and interface layout of the interface elements, the complexity of the current interface is calculated to obtain the display information.

[0033] Specifically, the formula for calculating interface complexity is:

[0034] in, The number of characters in the interface. The number of images in the interface. The complexity of the interface layout is represented by a, b, and c, which are the weighting coefficients of each parameter.

[0035] The weighting coefficients a, b, and c are allocated based on user experience testing and expert evaluation, generally following the principle of a > b > c. For example: , , When the interface contains 20 characters of text, 3 images, and a layout complexity of 5:

[0036] This embodiment calculates the interface complexity based on the type and number of interface elements and the interface layout, and uses this as the basis for interface color optimization. By dynamically balancing information density and visual comfort, it significantly improves the safety and efficiency of interaction in complex driving scenarios.

[0037] The steps S11 to S13 above are for illustrative purposes only and do not restrict the order in which data is collected.

[0038] In this embodiment, the optimization and adjustment requirements for scene switching are as follows: For example, ambient light can be categorized according to needs: Sunny day: Illumination intensity is between 30,000 and 130,000 lux, suitable for high-brightness lighting scenarios.

[0039] Cloudy day: Light intensity is between 3000 and 10000 lux, suitable for scenes with moderate brightness.

[0040] Dusk and dawn: The light intensity is around 300 lux, suitable for scenes requiring low brightness, etc. The vehicle speed can be divided into three stages according to the needs: For low speeds (≤30km / h), and to emphasize details, the interface contrast and brightness are appropriately increased, and the color temperature is warmer.

[0041] Medium speed (30-80km / h), emphasizing clarity, moderate interface brightness and contrast, and neutral color temperature.

[0042] High speed (≥80km / h), emphasizing information prominence, moderately increasing interface brightness and contrast, and slightly cool color temperature.

[0043] Interface complexity can be divided into three stages based on requirements: Low complexity (≤10), fully highlighting limited information content, improving interface contrast and brightness, and neutral color temperature.

[0044] Medium complexity (10-20), maintain visual comfort, avoid visual fatigue, keep interface contrast and brightness moderate, and neutral color temperature.

[0045] High complexity (≥20), reduce overall visual stress, highlight important content, reduce interface brightness, moderately increase contrast, and warm color temperature.

[0046] Therefore, it is necessary to calculate the comprehensive optimization coefficients and perform targeted color optimization.

[0047] S2. Based on a machine learning model, calculate the comprehensive optimization coefficient of the current interface corresponding to the current scene according to the environmental information, state information, and display information, including: S21. Determine the current scene type based on the environmental information and status information, and obtain the preset weight parameters of each target display attribute under the corresponding scene type; In this embodiment, the target display attributes in the interface display attributes include brightness, contrast, and color temperature.

[0048] For example, when the target display attribute is brightness, and based on the environmental information and status information, the current scene is a daytime low-speed driving scene, then the preset weight parameters corresponding to the environmental information, status information, and display information are respectively... , , The corresponding dynamic adjustment factors are α, β, and γ, respectively.

[0049]

[0050] In the formula, P1, P2, and P3 are the preset attribute scores of the current scene type class.

[0051] S22. Based on the dynamic adjustment algorithm, calculate the first weight coefficient according to the environmental information and the corresponding preset weight parameters, calculate the second weight coefficient according to the state information and the corresponding preset weight parameters, and calculate the third weight coefficient according to the display information and the corresponding preset weight parameters. In this embodiment, the dynamic adjustment algorithm is specifically as follows: Based on the collected data and preset weight parameters, the adjustment direction and the actual difference are determined. The actual difference is converted into an adjustment amplitude according to a preset proportional coefficient. The target weight corresponding to the collected data is calculated based on the adjustment direction and the adjustment amplitude. The collected data includes environmental information, status information, and display information.

[0052] Specifically, when the target display attribute is brightness; The formula for calculating the first weighting coefficient is as follows:

[0053] in, Preset weight parameters (preset scenario parameters, such as environmental information weights during daytime driving). For real-time acquisition of illumination parameters, These are the lighting parameters for the corresponding scene type; This is a dynamic adjustment coefficient used to control the degree of influence of changes in ambient light.

[0054] Similarly, the formula for calculating the second weighting coefficient is as follows:

[0055] in, Preset weight parameters (preset scenario parameters, such as the weight of state information during daytime driving). For real-time vehicle speed parameters, For the vehicle speed parameters in the corresponding scenario type; This is a dynamic adjustment coefficient used to control the degree of impact of changes in vehicle speed.

[0056] Similarly, the formula for calculating the third weighting coefficient is as follows:

[0057] in, Preset weight parameters (preset scene parameters, such as the weight of displayed information during daytime driving). This refers to the interface complexity parameters collected in real time. This refers to the interface complexity parameter for the corresponding scenario type. This is a dynamically adjustable coefficient used to control the degree of impact of changes in interface complexity.

[0058] Similarly, the calculation process for the first, second, and third weighting coefficients of contrast and color temperature is the same as that for brightness, only the dynamic adjustment coefficients and preset weighting parameters are different.

[0059] In this embodiment, when making dynamic adjustments, the collected data is compared with the preset weight parameters to determine the adjustment direction and the actual difference. The actual difference is converted into the adjustment amplitude according to the preset proportional coefficient. The target weight corresponding to the collected data is calculated based on the adjustment direction and the adjustment amplitude. The greater the change in the collected data, the greater the change in the weight. Thus, by combining real-time collected data, a proportional real-time dynamic adjustment is made to fully meet the needs of scene switching.

[0060] S23. Calculate the attribute scores of the environmental information, status information and display information for each target display attribute respectively; Specifically, the real-time collected environmental, status, and display information is input into the trained machine learning model architecture, and based on conventional scoring rules, an attribute score is output for each target's display attribute. This is a conventional machine learning model architecture (conventional scoring rules may include data processing steps such as feature extraction and deep neural network analysis), which will not be elaborated upon in this embodiment.

[0061] S24. Integrate the first weight coefficient, the second weight coefficient, the third weight coefficient, and the corresponding attribute score to calculate the comprehensive optimization coefficient of each target display attribute in the current scene; the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1.

[0062] The comprehensive optimization coefficient is calculated using a weighted average fusion algorithm, and its calculation formula is as follows:

[0063] In the formula, To comprehensively optimize the coefficients, , , These represent the first weighting coefficient, the second weighting coefficient, and the third weighting coefficient, respectively. , , These represent the attribute scores of the target display attributes for the environmental information, state information, and display information, respectively, while α, β, and γ represent the dynamic adjustment factors for the corresponding environmental information, state information, and display information under different scenarios.

[0064] This embodiment, on the one hand, calculates the weight coefficient by using preset weight parameters for each target display attribute under the corresponding scene type. Based on the real-time scene and the preset scene, it achieves integrated control between scene coefficients and dynamic adjustments, thereby simplifying the optimization difficulty, improving the optimization response sensitivity, and the adaptability of automatic color adjustment when scene switching is performed while performing precise color optimization. On the other hand, it integrates the first weight coefficient, the second weight coefficient, the third weight coefficient, and the corresponding attribute score to calculate the comprehensive optimization coefficient of each target display attribute under the current scene. It accurately judges the attribute score of different scene factors (environmental information, status information, and display information) on the user's reading interface, and then independently performs comprehensive automatic optimization of the target display attributes, effectively improving user satisfaction.

[0065] In this embodiment, when calculating the comprehensive optimization coefficient, a weighted average fusion algorithm is used to integrate environmental information, status information, and display information for color optimization, thereby achieving multi-dimensional error compensation. Real-time collected data is converted into attribute scores for the corresponding target display attributes, and adaptive adjustments are made based on the influence of actual scene factors on different target display attributes. At the same time, dynamic adjustment factors for corresponding environmental information, status information, and display information under different scenarios are incorporated to systematically evaluate the actual performance of each attribute of the interface and provide precise optimization strategies for different scenarios.

[0066] S3. Dynamically adjust the interface display attributes of the corresponding scene according to the comprehensive optimization coefficient. Specifically, obtain the comprehensive optimization coefficient corresponding to each target display attribute, calculate the target display parameters according to the comprehensive optimization coefficient and the current display parameters, and make smooth transition adjustments according to the preset step size.

[0067] The calculation formula for the target display parameters is as follows:

[0068] or,

[0069]

[0070] in, For the final displayed parameters, These are the preset parameters for the current scene. λ is the real-time calculated value, and λ is the smoothing factor, which controls the degree of integration between the scene coefficient and the dynamic adjustment.

[0071] This embodiment achieves a seamless and advanced experience in adjusting display attributes by using a preset step size for intelligent smooth transition, while ensuring driving safety.

[0072] S4. Based on the obtained user operation feedback, adjust the comprehensive optimization coefficient to further optimize the preset display attributes under different scenario interfaces, including: S41. Read user preferences; The user preferences include parameters such as interface brightness, contrast, and color temperature preset by the user, which are stored and retrieved by the system in real time.

[0073] The user-preferred interface brightness (Luser), contrast (Cuser), and color temperature (Tuser) parameters (normalized to the 0-1 range) are converted into a user preference index (Puser) using the following formula:

[0074] For example, if the user sets the brightness to 0.9, contrast to 0.7, and color temperature to 0.6, the weights are... , , ,but:

[0075] S42. Obtain user feedback on the interface display parameters after adjustment; S43. Based on the user operation feedback, determine the change parameters of the corresponding target display attributes, and adjust the preset weight parameters based on the change parameters and user preferences, update the comprehensive optimization coefficient, and further optimize the preset display parameters under different scenario interfaces.

[0076]

[0077] In the formula, For new user preferences (i.e., the adjusted preset weight parameters). The old user preferences (i.e., the preset weight parameters before adjustment). For user feedback, This includes environmental data (such as lighting, vehicle speed, and interface complexity).

[0078] This embodiment dynamically adjusts the comprehensive optimization coefficient and preset display parameters based on user operation feedback, which can significantly improve the personalized adaptability and scene optimization accuracy of the intelligent interactive interface.

[0079] Example 2 The accompanying drawings in this embodiment of the invention include: data acquisition module 1, scene recognition module 2, main control module 3, execution module 4, and personalization module 5.

[0080] This invention also provides a dynamic HMI color optimization system based on scene switching, used to implement the dynamic HMI color optimization method based on scene switching as described in Embodiment 1 above. See [link to embodiment]. Figure 2 It includes a data acquisition module 1, a scene recognition module 2, a main control module 3, an execution module 4, and a personalization module 5; the data acquisition module 1 is connected to the scene recognition module 2 and the main control module 3, and the main control module 3 is connected to the execution module 4 and the personalization module 5; The data acquisition module 1 is used to collect environmental information of the current scene in real time, obtain vehicle status information, and identify interface elements of the current interface. The scene recognition module 2 is used to determine the scene type of the current scene based on the environmental information and status information; The main control module 3 is used to analyze the complexity of the current interface based on the interface elements and use it as display information; it is also used to calculate the comprehensive optimization coefficient of the current interface corresponding to the current scene based on the environment information, state information and display information using a machine learning model. The execution module 4 is used to dynamically adjust the interface display attributes of the corresponding scenario according to the comprehensive optimization coefficient; The personalization module 5 is used to adjust the comprehensive optimization coefficient based on the obtained user operation feedback, and further optimize the preset display attributes under different scenario interfaces.

[0081] In this embodiment, the data acquisition module 1 includes an environmental perception sensor and a vehicle speed sensor; the environmental perception sensor includes at least one of a light sensor and a color temperature sensor.

[0082] The modules in this embodiment are used to implement the dynamic HMI color optimization method based on scene switching as described above.

[0083] This invention, based on a machine learning model, incorporates environmental, state, and display information to calculate the comprehensive optimization coefficient of the current interface for the current scene. This comprehensive optimization coefficient then dynamically adjusts the interface display attributes (brightness, contrast, and color temperature) for the corresponding scene. Adaptive color optimization is achieved through multi-variable weighting, and HMI display parameters are precisely optimized using comprehensive real-time data to improve display quality, thereby enhancing driving safety and information recognition efficiency, and ultimately improving user experience and visual comfort. Simultaneously, based on user operation feedback, the comprehensive optimization coefficient is adjusted to further optimize the preset display attributes under different scene interfaces, enhancing personalized user experience and reducing the risk of user distraction.

[0084] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A dynamic HMI color optimization method based on scene switching, characterized in that, include: Real-time collection of environmental information of the current scene and acquisition of vehicle status information; Identify the interface elements of the current interface, analyze the complexity of the current interface based on the interface elements, and use this as display information; Based on a machine learning model, the comprehensive optimization coefficient of the current interface corresponding to the current scene is calculated according to the environmental information, state information and display information. The interface display attributes for the corresponding scenario are dynamically adjusted based on the comprehensive optimization coefficients. Based on the user operation feedback obtained, the comprehensive optimization coefficient is adjusted to further optimize the preset display attributes under different scenario interfaces; Identify the interface elements of the current screen, analyze the complexity of the current screen based on the interface elements, and use this as display information, including: Identify the element types, element quantities, and interface layout of the current interface elements, where the element types include the number of text elements and the number of images. Based on the element types, element quantities, and interface layout of the interface elements, the complexity of the current interface is calculated to obtain the display information. The formula for calculating the complexity of the current interface is as follows: in, The number of characters in the interface. The number of images in the interface. a, b, and c represent the weighting coefficients of each parameter to indicate the complexity of the interface layout. The weighting coefficients a, b, and c are allocated based on user experience testing and expert evaluation, with the principle being a>b>c. Based on a machine learning model, the comprehensive optimization coefficient of the current interface is calculated according to the environmental information, state information, and display information, including: The current scene type is determined based on the environmental information and status information, and the preset weight parameters of each target display attribute under the corresponding scene type are obtained. Based on the dynamic adjustment algorithm, a first weight coefficient is calculated according to the environmental information and the corresponding preset weight parameters, a second weight coefficient is calculated according to the state information and the corresponding preset weight parameters, and a third weight coefficient is calculated according to the display information and the corresponding preset weight parameters. Calculate the attribute scores for each target display attribute for the environmental information, status information, and display information respectively; By integrating the first weight coefficient, the second weight coefficient, the third weight coefficient, and the corresponding attribute scores, a comprehensive optimization coefficient for each target display attribute in the current scene is calculated; the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1. The target display attributes in the interface display attributes include brightness, contrast, and color temperature; The comprehensive optimization coefficient is calculated using a weighted average fusion algorithm, and its calculation formula is as follows: In the formula, To comprehensively optimize the coefficients, , , These represent the first weighting coefficient, the second weighting coefficient, and the third weighting coefficient, respectively. , , These represent the attribute scores of the target display attributes for the environmental information, state information, and display information, respectively, while α, β, and γ represent the dynamic adjustment factors for the corresponding environmental information, state information, and display information under different scenarios.

2. The dynamic HMI color optimization method based on scene switching as described in claim 1, characterized in that, Real-time collection of environmental information from different scenarios and acquisition of vehicle status information, including: An environmental perception sensor is used to acquire and collect real-time illumination data of the current scene as environmental information. Vehicle speed sensors are used to monitor vehicle speed in real time and obtain vehicle status information.

3. The dynamic HMI color optimization method based on scene switching as described in claim 1, characterized in that, The dynamic adjustment algorithm is specifically as follows: Based on the collected data and preset weight parameters, the adjustment direction and the actual difference are determined. The actual difference is converted into an adjustment amplitude according to a preset proportional coefficient. The target weight corresponding to the collected data is calculated based on the adjustment direction and the adjustment amplitude. The collected data includes environmental information, status information, and display information.

4. The dynamic HMI color optimization method based on scene switching as described in claim 1, characterized in that, The interface display attributes of the corresponding scene are dynamically adjusted according to the comprehensive optimization coefficient. Specifically, the comprehensive optimization coefficient corresponding to each target display attribute is obtained, the target display parameters are calculated according to the comprehensive optimization coefficient and the current display parameters, and a smooth transition adjustment is performed according to the preset step size.

5. The dynamic HMI color optimization method based on scene switching as described in claim 1, characterized in that, Based on the obtained user operation feedback, the comprehensive optimization coefficient is adjusted to further optimize the preset display parameters under different scenario interfaces, including: Read user preferences; Obtain user feedback after adjusting the interface display parameters; Based on the user operation feedback, the change parameters of the corresponding target display attributes are determined, and the preset weight parameters are adjusted based on the change parameters and user preferences. The comprehensive optimization coefficient is then updated to further optimize the preset display parameters under different scenario interfaces.

6. A dynamic HMI color optimization system based on scene switching, used to implement the dynamic HMI color optimization method based on scene switching as described in any one of claims 1 to 5, characterized in that: It includes a data acquisition module, a scene recognition module, a main control module, an execution module, and a personalization module; the data acquisition module is connected to the scene recognition module and the main control module, and the main control module is connected to the execution module and the personalization module. The data acquisition module is used to collect environmental information of the current scene in real time, obtain vehicle status information, and identify interface elements of the current interface. The scene recognition module is used to determine the scene type of the current scene based on the environmental information and status information; The main control module is used to analyze the complexity of the current interface based on the interface elements and use it as display information; it is also used to calculate the comprehensive optimization coefficient of the current interface corresponding to the current scene based on the environment information, state information and display information using a machine learning model. The execution module is used to dynamically adjust the interface display attributes of the corresponding scenario according to the comprehensive optimization coefficient; The personalization module is used to adjust the comprehensive optimization coefficient based on the obtained user operation feedback, and further optimize the preset display attributes under different scenario interfaces.

7. The dynamic HMI color optimization system based on scene switching as described in claim 6, characterized in that: The data acquisition module includes an environmental perception sensor and a vehicle speed sensor; the environmental perception sensor includes at least one of a light sensor and a color temperature sensor.

Images