Color matching engineering efficiency improving method and device based on large model

Abstract

The invention discloses a color matching engineering efficiency improving method and device based on a large model, and belongs to the technical field of vehicle color matching. The method comprises the steps of collecting color matching data; importing vehicle data of a vehicle to be subjected to color matching to the trained color matching model to obtain a color matching suggestion; processing a vehicle model of the vehicle to be subjected to color matching based on the color matching suggestion, the vehicle data and a color reconciling algorithm to generate a second vehicle color matching model; processing the second vehicle color matching model based on the environment model to obtain a vehicle external effect; the second vehicle color matching model is processed based on the light source data in combination with a color physics algorithm to determine vehicle interior effects of the vehicle under different light source settings. According to the method, the technical effect of improving the vehicle color matching design efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle color matching, and in particular to a method and device for improving the efficiency of color matching engineering based on a large model. Background Art

[0002] In today's automotive industry, vehicle color design is not only an important means to shape the brand image and attract consumers' attention, but also a key factor in reflecting the individuality and differentiated competition of automobiles. As consumers' pursuit of the beauty of automobile appearance increases and competition in the automobile market becomes increasingly fierce, the complexity and importance of vehicle color design are becoming increasingly prominent.

[0003] The traditional vehicle color design process often relies on the designer's personal experience and artistic sense, and achieves satisfactory color matching effects through repeated manual color testing and adjustments. However, this method has many limitations. First, the lack of scientific data support and systematic design methods leads to greater randomness and uncertainty in color design. Secondly, the traditional color design process is time-consuming and inefficient, and it is difficult to meet the fast-paced and high-efficiency requirements of modern automobile production. Especially in the context of the current rapid changes in the automobile market, consumers' preferences for vehicle colors are also constantly changing. In order to keep up with market trends and meet the diverse needs of consumers, automobile manufacturers need to frequently launch new color schemes. This requires the vehicle color design process to be more efficient and flexible, and to be able to respond quickly to market changes.

[0004] Therefore, how to improve the efficiency of vehicle color matching design has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a large-model-based color engineering efficiency improvement method and device to solve the following technical problem: how to improve the efficiency of vehicle color design.

[0006] In a first aspect, an embodiment of the present application provides a color engineering efficiency improvement method based on a large model, characterized in that the method includes: collecting color matching data; wherein the color matching data includes vehicle color matching data and color matching data, and the vehicle color matching data includes vehicle external color matching data and vehicle internal color matching data; importing vehicle data of a vehicle to be matched to a trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure, and configuration; processing the vehicle model of the vehicle to be matched based on the color matching suggestions to generate a first vehicle color matching model equipped with color matching suggestions; adjusting the contrast, saturation, and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color harmony algorithm to generate a second vehicle color matching model; processing the second vehicle color matching model based on a preset environmental model to obtain the vehicle external effects under different external environments; determining the in-vehicle light source data based on the vehicle data; wherein the in-vehicle light source data includes light source position, light source brightness, light source structure, and light source setting; processing the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle internal effects under different light source settings.

[0007] In one implementation of the present application, before importing vehicle data of a vehicle to be color-matched into a trained color-matching model to obtain color-matching suggestions, the method further includes: constructing a color-matching model based on a preset convolutional neural network and a preset long short-term memory network; wherein the convolutional neural network is used to identify image features in the color-matching data, and the long short-term memory network is used to process time series information in the color-matching data; cleaning and arranging the color-matching data, removing outliers and noise data, to generate sample data; wherein the sample data is data in a uniform format, and the sample data includes a training set, a test set, and a validation set; training and validating the color-matching model based on the sample data, and evaluating the generalization ability of the color-matching model based on a preset cross-validation strategy; optimizing the parameters of the color-matching model based on a preset back-propagation algorithm; and generating a trained color-matching model when the performance of the color-matching model on the validation set reaches a preset accuracy threshold.

[0008] In one implementation of the present application, vehicle data of a vehicle to be colored is imported into a trained color matching model to obtain color matching suggestions, specifically including: preprocessing the vehicle data of the vehicle to be colored to generate input data; wherein the input data is in a format recognizable by the trained color matching model; importing the input data into the trained color matching model; and the color matching model outputs color matching suggestions corresponding to the input data based on feature information of the input data.

[0009] In one implementation of the present application, a vehicle model of a vehicle to be color matched is processed based on color matching suggestions to generate a first vehicle color matching model equipped with color matching suggestions, specifically including: determining the color matching suggestions; wherein the color matching suggestions include color suggestions and material suggestions for multiple components; establishing a three-dimensional model of the vehicle to be color matched based on a preset three-dimensional modeling software; wherein the three-dimensional model includes multiple components; matching the color matching suggestions with the three-dimensional model based on the components to generate a first vehicle color matching model; wherein some components in the first vehicle color matching model may not be colored.

[0010] In one implementation of the present application, the contrast, saturation and brightness of the colors in the first vehicle color matching model are adjusted based on vehicle data and a preset color harmony algorithm to generate a second vehicle color matching model, specifically including: processing the first vehicle color matching model and vehicle data to determine the design style and color matching tone of the vehicle to be matched; according to the color harmony algorithm, calculating the contrast, saturation and brightness relationship between the components in the first vehicle color matching model, and referring to the design style and color matching tone to identify the disharmonious factors in the first vehicle color matching model; wherein the disharmonious factors are colors that are inconsistent with the design style and color matching tone; removing the disharmonious factors to generate a vehicle color matching model to be filled; filling the vehicle color matching model to be filled according to the design style and color matching tone to generate a second vehicle color matching model.

[0011] In one implementation of the present application, a second vehicle color matching model is processed based on a preset environmental model to obtain vehicle exterior effects under different external environments, specifically including: constructing a multi-environment simulation system; wherein the multi-environment simulation system includes multiple scenes and multiple weathers; importing the second vehicle color matching model into the multi-environment simulation system; processing the second vehicle color matching model based on a preset rendering algorithm to determine the vehicle exterior effect.

[0012] In one implementation of the present application, the second vehicle color matching model is processed based on a preset rendering algorithm to generate a set of vehicle exterior effect images, specifically including: setting rendering parameters; wherein the rendering parameters include lighting conditions, shadow effects, reflectivity, refractive index, and environment map; performing multi-angle rendering on the second vehicle color matching model to generate vehicle exterior effect images containing different perspectives; according to preset time periods and weather conditions, adjusting the lighting and weather effects in the rendering environment to generate vehicle exterior effect images under different time periods and weather conditions.

[0013] In one implementation of the present application, a second vehicle color matching model is processed based on light source data and in combination with a preset color physics algorithm to determine the interior effects of the vehicle under different light source settings, specifically including: establishing a light source simulation environment; wherein the light source simulation environment is configured according to the light source data; importing the second vehicle color matching model into the light source simulation environment; applying a color physics algorithm to perform lighting simulation on the second vehicle color matching model based on the spectral characteristics of the light source, the reflection and absorption characteristics of the material, and the visual characteristics of the human eye; calculating and generating color rendering effects of various components of the vehicle interior under different light source settings; wherein the color rendering effects include color changes, shadow distribution, and highlight effects; outputting the color rendering effects as a vehicle interior effect image set to generate a vehicle interior color matching effect.

[0014] In one implementation of the present application, the method also includes: establishing a color evaluation index; wherein the color evaluation index includes color harmony, visual comfort, spatial perception, and material texture performance; processing the vehicle interior effect and the vehicle exterior effect based on a preset image analysis algorithm to extract color feature parameters; wherein the color feature parameters include at least hue, brightness, and saturation; and calculating the color evaluation scores of the vehicle interior effect and the vehicle exterior effect based on the color evaluation index.

[0015] In the second aspect, the embodiment of the present application also provides a color engineering efficiency improvement device based on a large model, the device comprising: a data acquisition module, for collecting color matching data; wherein the color matching data includes vehicle color matching data and color matching data; the vehicle color matching data includes vehicle external color matching data and vehicle internal color matching data; a color matching suggestion generation module, for importing vehicle data of a vehicle to be matched into a trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure and configuration; a first vehicle model generation module, for processing a vehicle model of a vehicle to be matched based on the color matching suggestion, to generate a first vehicle color matching model equipped with a color matching suggestion; a second vehicle model generation module, for A module for adjusting the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color harmony algorithm to generate a second vehicle color matching model; a vehicle exterior color module for processing the second vehicle color matching model based on a preset environment model to obtain the vehicle exterior effects under different external environments; a light source data determination module for determining the vehicle interior light source data based on the vehicle data; wherein the vehicle interior light source data includes the light source position, light source brightness, light source structure and light source setting; a vehicle interior color module for processing the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effects under different light source settings.

[0016] The embodiment of the present application provides a color matching engineering efficiency improvement method and device based on a large model, which has at least the following technical effects:

[0017] By collecting comprehensive color matching data, including color matching data of the vehicle's exterior and interior, as well as color matching data, rich and accurate samples are provided for the training of the color matching model. By establishing and training the color matching model, the present invention can intelligently output reasonable color matching suggestions based on the input data such as the vehicle model, publicity, structure and configuration of the vehicle to be matched, thereby greatly improving the efficiency and accuracy of the color matching design; based on the color matching suggestions, the present invention can further process the vehicle model of the vehicle to be matched, and generate a first vehicle color matching model equipped with color matching suggestions; through the preset color harmony algorithm, the present invention can also adjust the contrast, saturation and brightness of the colors in the first vehicle color matching model, thereby generating a more harmonious and beautiful second vehicle color matching model. In addition, the present invention also uses the preset environmental model and color physics algorithm to simulate the vehicle's external effects under different external environments and the vehicle's internal effects under different light source settings, thereby improving the efficiency of vehicle color matching design. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A flow chart of a color matching engineering efficiency improvement method based on a large model provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a color matching engineering efficiency improvement device based on a large model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0022] The embodiments of the present application provide a large-model-based color engineering efficiency improvement method and device to solve the following technical problem: how to improve the efficiency of vehicle color design.

[0023] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0024] Figure 1 A flow chart of a color matching engineering efficiency improvement method based on a large model provided in an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a color matching engineering efficiency improvement method based on a large model, which specifically includes the following steps:

[0025] Step 1: Collect color matching data, wherein the color matching data includes vehicle color matching data and color matching data. The vehicle color matching data includes vehicle exterior color matching data and vehicle interior color matching data.

[0026] This step aims to collect comprehensive color matching data to provide a basis for subsequent color matching model training. Color matching data mainly includes vehicle color matching data and color matching data. Vehicle color matching data is further subdivided into vehicle exterior color matching data and vehicle interior color matching data, covering vehicle color schemes of various models, years, and market positioning, as well as interior decoration color matching designs.

[0027] Color matching data: refers to all relevant data used for color scheme generation, optimization or analysis, including but not limited to color codes, color matching rules, color usage cases in actual application scenarios, etc.

[0028] Vehicle exterior color data: Color information of the visible parts of the vehicle, such as the vehicle shell, body, and windows. Exterior color data of various types of vehicles. For example, the standard color schemes of vehicles of different brands and models, as well as the preferences and trends of user-customized color schemes can be recorded.

[0029] Vehicle interior color data: color information of the vehicle interior, such as seats, dashboard, door panels, etc.

[0030] Similar to the collection of vehicle exterior color data, vehicle interior color data is collected by accessing the internal design data of automobile manufacturers, cooperating with interior suppliers, and analyzing user feedback, such as the impact of different materials (such as leather, fabric, plastic, etc.) on color rendering.

[0031] Color matching data: A dataset that shows how colors are combined to produce visual beauty or specific emotional responses in different application scenarios.

[0032] Collect information through market research, automobile manufacturer databases, and online automobile sales platforms.

[0033] By analyzing fashion magazines, design websites, artworks and other sources, we can collect color matching data. This data can include color matching rules (such as contrasting colors, adjacent colors, complementary colors, etc.), color psychology applications (such as warm colors stimulate appetite, cool colors promote calmness, etc.), and color preferences in specific cultures or regions; we can also use big data analysis technology to explore users' preferences and trends for color matching from social media, e-commerce platforms and other channels.

[0034] In the embodiment of the present application, the automobile manufacturer collects color matching data in order to develop the color matching scheme of the new generation of models:

[0035] Extract standard color schemes for existing models from the automaker's database, including color codes and color matching ratios. Based on image recognition technology, extract additional color information from official vehicle photos, such as color details of special paint versions. Through market research, collect user preferences and trends for vehicle exterior color matching, such as the popularity of specific colors or color combinations among young consumers.

[0036] Access the internal design materials of automobile manufacturers to obtain the design concepts and principles of interior color matching. Work with interior suppliers to understand the impact of different materials on color rendering, and collect actual samples for color analysis. Analyze user feedback to understand the impact of interior color matching on user driving experience and emotions, such as whether certain color combinations are more likely to cause driving fatigue.

[0037] Collect color matching rules and application cases from fashion magazines and design websites to understand the current popular color trends and matching methods. Use big data analysis technology to mine users' preferences and trends for color matching from social media and e-commerce platforms, such as the popularity of specific color combinations in clothing, household items, etc. Combined with the principles of color psychology, analyze the impact of different color matching on user emotional responses.

[0038] Before executing step 2, you need to build and train the color matching model, which includes the following steps:

[0039] Step A1: construct a color matching model based on a preset convolutional neural network and a preset long short-term memory network; wherein the convolutional neural network is used to identify image features in color matching data, and the long short-term memory network is used to process time series information in the color matching data.

[0040] Convolutional Neural Network (CNN): A feed-forward neural network that is particularly suitable for processing data with grid-like topological structures, such as images. It can automatically extract feature information in images, such as edges, textures, etc., through structures such as convolutional layers, pooling layers, and fully connected layers.

[0041] Long Short-Term Memory (LSTM): A special type of recurrent neural network (RNN) that can handle long-term dependencies in sequence data. It can effectively retain and utilize key information in sequence data by introducing memory units and gating mechanisms.

[0042] In the embodiment of the present application, a convolutional neural network is used to identify image features in color matching data. For example, in vehicle color matching, CNN can extract features such as color distribution and texture pattern in the vehicle body image. Long short-term memory network is used to process the time series information in the color matching data. For example, market trends and user preference changes in different time periods, LSTM can provide additional contextual information to help the model generate color matching suggestions that are more in line with market needs.

[0043] By combining CNN and LSTM, we can build a color matching model that can process image features and consider temporal information.

[0044] Step A2: clean and organize the color matching data, remove outliers and noise data, and generate sample data; wherein the sample data is data in a unified format, and the sample data includes a training set, a test set, and a validation set.

[0045] Outliers: Values ​​that deviate significantly from other data points in a data set, which may be caused by measurement errors, data entry errors, or unusual events.

[0046] Noisy data: Random errors or fluctuations in a data set that interfere with useful information.

[0047] Sample data: After cleaning and organization, the data set used to train and test the model includes training set, test set and validation set.

[0048] In the embodiment of the present application: For the collected vehicle color matching data, data cleaning is first performed. By checking the color code, texture description and other information of each vehicle model, obvious outliers (such as wrong color codes, missing texture descriptions, etc.) are identified and removed. Then, the data is sorted. All image data are adjusted to the same resolution (such as 128x128 pixels) and color space (such as RGB color space), and all text data are converted to UTF-8 encoding format. Finally, the data set is divided into a training set (accounting for 70% of the total data), a test set (accounting for 20% of the total data) and a validation set (accounting for 10% of the total data) for subsequent training and testing.

[0049] Step A3: training and validating the color matching model based on the sample data, and evaluating the generalization ability of the color matching model based on a preset cross-validation strategy.

[0050] Model training: The process of learning a model using training set data, aiming to adjust the parameters and structure of the model to minimize the loss function.

[0051] Model validation: The process of evaluating the trained model using validation set data to check the generalization ability of the model and prevent overfitting.

[0052] Cross-validation: A statistical method for evaluating the generalization ability of a model. It divides the dataset into multiple subsets and uses each subset as a validation set to train the model in turn, thereby obtaining performance evaluation results of multiple models.

[0053] In the embodiment of the present application: For the vehicle color matching model, CNN and LSTM are jointly trained using the training set data. The parameters and structure of the model are adjusted to minimize the cross entropy loss function. During the training process, the model is regularly evaluated using the validation set data to check the generalization ability of the model and prevent overfitting. In order to more comprehensively evaluate the performance of the model, a 5-fold cross-validation strategy is adopted. The data set is divided into 5 subsets, and each subset is used as a validation set in turn to train the model. Then, the average values ​​of indicators such as accuracy, recall, and F1 score of each model are calculated as the final model performance evaluation result.

[0054] Step A4: Optimize the parameters of the color matching model based on a preset back propagation algorithm.

[0055] Backpropagation algorithm: An algorithm for training artificial neural networks that calculates the gradient of the loss function with respect to the model parameters and updates the parameters in the opposite direction of the gradient to minimize the loss function.

[0056] In the embodiment of the present application: For the vehicle color matching model, the back propagation algorithm is used to optimize the parameters of CNN and LSTM during the training process. First, the gradient of the cross entropy loss function with respect to the model parameters is calculated. Then, the Adam optimizer is used to update the parameters in the opposite direction of the gradient to minimize the loss function. During the optimization process, the changes in the loss function are regularly monitored, and the optimization parameters such as the learning rate are adjusted as needed to ensure the convergence and performance improvement of the model.

[0057] Step A5: When the performance of the color matching model on the validation set reaches a preset accuracy threshold, a trained color matching model is generated.

[0058] Accuracy threshold: A performance indicator threshold set during the model training process. When the performance of the model on the validation set reaches this threshold, the model is considered to have been fully trained and training can be stopped.

[0059] In an embodiment of the present application: For the vehicle color matching model, the validation set data is used regularly during the training process to evaluate the model, and performance indicators such as accuracy are calculated. When the accuracy of the model on the validation set reaches more than 90% for multiple consecutive times (such as 5 times), the model is considered to have been fully trained and training can be stopped. At this point, the trained model is saved for subsequent use. When saving the model, the parameters and structural information of the model and the relevant configuration information during the training process (such as the learning rate is set to 0.001, using the Adam optimizer, etc.) are recorded. In this way, when designing color schemes for other models or brands in the future, this trained model can be used directly to generate high-quality color matching suggestions.

[0060] Step 2: Import the vehicle data of the vehicle to be color matched into the trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure and configuration.

[0061] Vehicle data: refers to the relevant information of the vehicle to be color matched, including but not limited to the model, publicity, structure and configuration, etc. These data are the basis for the color matching model to generate color matching suggestions.

[0062] Color suggestion: Based on vehicle data and the trained color model, the model outputs a color scheme or suggestion for a specific vehicle.

[0063] Step 21 : pre-process the vehicle data of the vehicle to be color matched to generate input data; wherein the input data is in a format that can be recognized by the trained color matching model.

[0064] Data preprocessing: Before importing the data into the color matching model, the raw data is cleaned, converted, and formatted to generate input data that meets the model input requirements.

[0065] Input data: Formatted data that can be recognized by the trained color matching model after preprocessing.

[0066] Data preprocessing is a key step to ensure that the color matching model can accurately understand the vehicle data and generate effective color matching recommendations. The preprocessing process may include data cleaning (such as removing duplicate data, correcting erroneous data, etc.), data conversion (such as converting text data into numerical data, adjusting image data to a uniform resolution, etc.) and data formatting (such as organizing data into a specific data structure or format).

[0067] For vehicle data, the following preprocessing operations are required:

[0068] Vehicle model data: Convert vehicle model names into standardized codes so that the model can recognize the differences between different vehicle models.

[0069] Promotional data: Extract key information from promotional materials (such as vehicle color, style description, etc.) and convert it into numerical or text vector form for model analysis and processing.

[0070] Structural data: Convert vehicle body structural information (such as the number of doors, seat layout, etc.) into numerical form and encode or normalize it.

[0071] Configuration data: Convert configuration information (such as interior light strips, displays, etc.) into numerical form and perform standardization or normalization.

[0072] In the embodiment of the present application: for the vehicle data of the SUV model, the following preprocessing operations are performed:

[0073] Convert the model name into a unique identifier (such as "SUV_Model_A"), extract the vehicle color and style description from the promotional materials and convert them into text vector form, convert the body structure information (such as five doors and five seats, four-wheel drive system, etc.) into numerical coding form, convert the configuration information (such as interior light strips, displays, etc.) into numerical form and normalize them.

[0074] Step 22: Import the input data into the trained color matching model.

[0075] The embodiment of step 31 is used as follows: for the vehicle data of SUV models, the image data (such as vehicle promotional pictures) is adjusted to a uniform resolution and color space and input into the model as one dimension of the tensor; the text data (such as the model name, style description, etc.) is converted into a text vector form and input into the model as another dimension; the structure data and configuration data are input into the model as additional feature dimensions.

[0076] Step 23: The color matching model outputs color matching suggestions corresponding to the input data based on the feature information of the input data.

[0077] Feature information: key information extracted from the input data to describe vehicle characteristics, such as vehicle model, color preference, body structure, etc.

[0078] The embodiment of step 22 is used as follows: after receiving the pre-processed input data, the color matching model starts to process and analyze it. The model first extracts feature information such as color distribution and texture pattern in the vehicle promotional pictures through CNN, and then processes other feature information such as model name, style description, body structure and configuration through LSTM. Based on these extracted feature information, the color matching model generates color matching suggestions for the SUV model. The suggestions include recommended color combinations (such as the combination of black body and silver wheels), color matching styles (such as sports style or luxury style), and color matching proportions (such as the ratio between the main color and the auxiliary color of the body).

[0079] Step 3: Process the vehicle model of the vehicle to be color matched based on the color matching suggestion to generate a first vehicle color matching model equipped with the color matching suggestion.

[0080] Step 31: Determine color matching suggestions; wherein the color matching suggestions include color suggestions and material suggestions for multiple components.

[0081] Color suggestion: In this step, the color suggestion refers to a comprehensive suggestion including color suggestions and material suggestions for multiple parts generated by the color matching model based on the vehicle data of the vehicle to be matched. The color suggestion involves a specific color code, while the material suggestion includes various material types such as metal, plastic, leather, etc.

[0082] For example, the color matching model generates detailed color matching suggestions based on the car model, publicity, structure and configuration data. The color matching suggestions include dark blue metallic paint for the body, brown leather for the interior seats, and silver plastic trim for the dashboard and door panels.

[0083] Step 32: Create a three-dimensional model of the vehicle to be color-matched based on a preset three-dimensional modeling software; wherein the three-dimensional model includes a plurality of components.

[0084] 3D modeling software: Professional software for creating and editing 3D models, such as 3ds Max, Maya, and Blender.

[0085] 3D model: A virtual vehicle model created based on 3D modeling software, which contains various components and details of the vehicle, such as the body, windows, wheels, and interior.

[0086] For example, the designer chooses to use 3ds Max software to build a 3D model of the vehicle to be colored, or directly obtains a 3D image of the vehicle with color matching from the vehicle R&D department.

[0087] Step 33: Generate a first vehicle color matching model based on the component matching color matching suggestions and the three-dimensional model; wherein some components in the first vehicle color matching model may not be colored.

[0088] Component matching: The process of matching the color and material information in the color matching suggestion with each component in the 3D model.

[0089] The first vehicle color matching model: a three-dimensional model containing color matching suggestions generated based on the component matching results. The model shows the color and material effects of each component of the vehicle.

[0090] In the embodiment of the present application, when matching the color matching suggestion with the 3D model, the various components in the 3D model of the vehicle, such as the body, windows, wheels, interior, etc., are first identified and classified according to their functions and locations. Then, the deep blue metallic paint in the color matching suggestion is applied to the body parts, the brown leather material is applied to the interior seat parts, and the silver brushed metal trim is applied to the instrument panel and door panel parts. However, some wheel hubs and detail parts have not yet been colored.

[0091] It is understandable that the uncolored portion may be a component that is extra on the vehicle to be colored compared to other vehicles, such as a display frame on the roof.

[0092] Step 4: Adjust the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color harmony algorithm to generate a second vehicle color matching model.

[0093] Color harmony algorithm: A mathematical or computational model used to adjust and optimize color matching. The algorithm achieves precise control of color matching by calculating parameters such as contrast, saturation, and brightness between colors.

[0094] Contrast: refers to the difference in brightness between two or more colors, and is one of the important factors affecting visual effects in color matching.

[0095] Saturation: refers to the purity or brightness of color. The higher the saturation, the brighter the color; the lower the saturation, the darker the color.

[0096] Brightness: refers to the lightness or darkness of a color. The higher the brightness, the brighter the color; the lower the brightness, the darker the color.

[0097] Step 41: Process the first vehicle color matching model and the vehicle data to determine the design style and color matching tone of the vehicle to be matched.

[0098] Design style: refers to the artistic style and characteristics presented by the overall design of the vehicle, such as luxury, sportiness, simplicity, etc.

[0099] Color matching tone: refers to the combination of primary and secondary colors used in vehicle color matching.

[0100] When determining the design style and color matching tone of the vehicle to be matched, multiple factors such as vehicle data, market demand and brand positioning need to be considered comprehensively. First, the vehicle data needs to be analyzed in detail, including model, size, purpose, target consumer group, etc. Then, the overall design style of the vehicle is determined in combination with market demand and brand positioning. For example, for a sports car targeting young consumers, a dynamic and colorful design style may be adopted.

[0101] For example, taking a luxury car for young consumers as an example, after determining the overall design style of the model as a combination of luxury and sportiness, the color matching tone is further determined. The color matching tone is the main color and auxiliary color of the first vehicle color matching model, such as main red and auxiliary silver.

[0102] Step 42: Calculate the contrast, saturation and brightness relationship between the components in the first vehicle color matching model according to the color harmony algorithm, and refer to the design style and color matching tone to identify the disharmonious factors in the first vehicle color matching model; wherein the disharmonious factors are colors that are inconsistent with the design style and color matching tone.

[0103] Disharmonious factors: refers to the colors or color matching methods that are inconsistent with the design style and color matching tone in the first vehicle color matching model.

[0104] In the embodiment of the present application: in the first vehicle color matching model of the above-mentioned luxury sedan, through the calculation and analysis of the color harmony algorithm, it is found that the color of the antenna on the roof has a significant contrast difference with the main color red of the body, and the saturation is too high, which looks too abrupt. This is inconsistent with the overall design style of the vehicle that combines luxury and sportiness, and is therefore identified as a disharmonious factor.

[0105] Step 43: Remove the inharmonious factors to generate a color matching model of the vehicle to be filled.

[0106] In the embodiment of the present application: in the above-mentioned luxury car example, the antenna color is deleted. The adjusted model is the vehicle color matching model to be filled.

[0107] Step 44: fill the vehicle color matching model to be filled according to the design style and color matching tone to generate a second vehicle color matching model.

[0108] In the embodiment of the present application: in the above-mentioned luxury car example, according to the design style combining luxury and sports and the color matching tone of red as the main color and silver as the auxiliary color, the color matching model of the vehicle to be filled is filled. Red and silver tones are selected to complement the antenna color.

[0109] Step 5: Process the second vehicle color matching model based on the preset environment model to obtain the vehicle exterior effects under different external environments.

[0110] Step 51: construct a multi-environment simulation system; wherein the multi-environment simulation system includes multiple scenes and multiple weather conditions.

[0111] Multi-environment simulation system: This system is a virtual environment that integrates multiple scenes and weather conditions to simulate the performance of vehicles in different external environments. Through this system, the visual effects of vehicle colors under different conditions can be fully evaluated, providing strong support for the optimization of color schemes.

[0112] First, build a variety of scenes, such as urban roads, highways, country roads, mountain roads, etc. Each scene contains detailed elements such as roads, buildings, vegetation, etc. to simulate the real external environment. In addition to scene construction, set a variety of weather conditions, such as sunny, cloudy, rainy, snowy, etc. Each weather condition contains corresponding parameters such as lighting, shadows, reflections, etc. to accurately simulate the visual effects under different weather conditions. In order to more accurately simulate the visual effects under different environments, users are allowed to fine-tune the relevant parameters of the scene and weather conditions. For example, users can adjust the intensity and direction of the light, the softness and depth of the shadow, the intensity and color of the reflection, etc.

[0113] In the embodiment of this application: a color scheme is being designed for an SUV model. First, a multi-environment simulation system including two scenes of urban roads and highways is constructed. Then three weather conditions of sunny, cloudy and rainy days are set. By adjusting parameters such as lighting, shadows and reflections.

[0114] Step 52: Import the second vehicle color matching model into the multi-environment simulation system.

[0115] Before importing, the second vehicle color matching model needs to be converted into a format suitable for the simulation system. After the data preparation is completed, the vehicle color matching model is imported into the multi-environment simulation system. After the import is completed, the vehicle color matching model is verified.

[0116] Step 53: Process the second vehicle color matching model based on a preset rendering algorithm to determine the vehicle exterior effect.

[0117] Rendering algorithm is a computational method used to generate high-quality images. In vehicle color matching design, rendering algorithm is used to simulate the exterior effect of the vehicle in different environments. Through rendering algorithm, the vehicle exterior effect images containing different viewing angles, lighting conditions and weather effects can be generated, providing intuitive support for the optimization of color matching schemes.

[0118] Step 531, setting rendering parameters; wherein the rendering parameters include lighting conditions, shadow effects, reflectivity, refractive index and environment map.

[0119] Lighting conditions: Lighting conditions are one of the most important parameters in the rendering process. It determines the brightness and color performance of objects in the scene. You can set different lighting conditions according to actual needs, such as natural light and artificial light.

[0120] Shadow effect: Shadow effect is one of the important factors to enhance the realism of the scene. By adjusting the softness and depth of the shadow, you can simulate a more realistic shadow effect.

[0121] Reflectivity: Reflectivity determines the intensity of light reflected from the surface of an object. By adjusting the reflectivity parameter, you can simulate the reflection effect of different material surfaces.

[0122] Refractive index: The refractive index is a physical quantity that describes the phenomenon of light refraction on the surface of an object. During the rendering process, the visual effect of transparent or translucent objects can be simulated by adjusting the refractive index parameters.

[0123] Environment map: Environment map is a technology used to simulate the background of the scene. By adding environment map, the system can provide richer background details and color performance for the scene.

[0124] In the embodiment of the present application: when rendering an SUV model, natural light is set as the lighting condition, and parameters such as the softness and depth of the shadow are adjusted to enhance the realism of the scene. At the same time, the reflectivity and refractive index parameters of different material surfaces are set to simulate the real material effect. Finally, an environment map containing the sky and distant mountains is added to provide richer background details.

[0125] Step 532: Perform multi-angle rendering on the second vehicle color matching model to generate vehicle exterior effect images containing different viewing angles.

[0126] Multi-angle rendering: Multi-angle rendering is a technique used to generate images of objects from different perspectives. In vehicle color matching design, multi-angle rendering can help users more comprehensively evaluate the performance of vehicle colors from different perspectives.

[0127] In this application example, when rendering an SUV model, three perspectives were selected for rendering: front, side, and top. In terms of rendering settings, a high rendering resolution and appropriate anti-aliasing parameters were set to ensure high-quality images. After rendering, the vehicle's exterior renderings from different perspectives were generated.

[0128] Step 533: Adjust the lighting and weather effects in the rendering environment according to the preset time period and weather conditions to generate vehicle exterior effect images under different time periods and weather conditions.

[0129] Time period and weather conditions: In vehicle color matching design, time period and weather conditions are one of the important factors affecting the vehicle's exterior effect.

[0130] Referring to step 532, in the embodiment of the present application: in order to simulate the exterior effects of the SUV model in different time periods and weather conditions, three time periods of morning, noon and evening are set, and the corresponding lighting conditions and color expressions are adjusted respectively. At the same time, two weather types of sunny and rainy days are set, and corresponding effects such as shadows and reflections are added. By simulating the lighting and weather effects in different time periods and weather conditions, a vehicle exterior effect image containing multiple scenes is generated.

[0131] Step 6: Determine the in-vehicle light source data based on the vehicle data; wherein the in-vehicle light source data includes the light source position, light source brightness, light source structure and light source setting.

[0132] In-vehicle light source data: In-vehicle light source data refers to the specific information of the vehicle's internal light source, including but not limited to the light source position, light source brightness, light source structure, and light source settings. These data have an important impact on the effect of the vehicle's interior color matching, because different light source data will lead to differences in color performance. By accurately obtaining and setting the in-vehicle light source data, the stability and aesthetics of the vehicle's interior color matching scheme can be ensured under different lighting conditions.

[0133] Light source position: Light source position refers to the installation position of the interior light source in the vehicle. Different light source positions will have a significant impact on the light distribution and color performance inside the vehicle. For example, the different positions of the roof light and reading light will result in different light intensity and color saturation in different areas of the vehicle.

[0134] Light source brightness: Light source brightness refers to the intensity of the light emitted by the light source. In the vehicle interior color matching, light source brightness directly affects the brightness and contrast of the color. Reasonable setting of light source brightness can ensure the stability and readability of the vehicle interior color under different lighting conditions.

[0135] Light source brightness: Light source structure refers to the physical form and components of the light source. Light sources with different functions emit different amounts of light, such as reading lights and ambient lights.

[0136] Step 7: Process the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effects under different light source settings.

[0137] Step 71: Establish a light source simulation environment; wherein the light source simulation environment is configured according to the light source data.

[0138] Light source simulation environment: A virtual environment used to simulate the lighting conditions inside the vehicle under different light source settings. The environment is configured based on light source data (including light source position, brightness, structure, etc.) to reflect the actual lighting conditions inside the vehicle.

[0139] Step 72: Import the second vehicle color matching model into the light source simulation environment.

[0140] Same as step 52, which will not be described in detail here.

[0141] Step 73: Apply a color physics algorithm to perform lighting simulation on the second vehicle color matching model based on the spectral characteristics of the light source, the reflection and absorption characteristics of the material, and the visual characteristics of the human eye.

[0142] Spectral characteristics: The wavelength distribution of light emitted by a light source determines the color of the light.

[0143] Reflection and absorption characteristics of materials: The ability of the surface materials of various components inside the vehicle to reflect and absorb light affects the color performance.

[0144] Human visual characteristics: the human eye's ability to perceive color, including color brightness, saturation, and contrast.

[0145] Step 74: Calculate and generate color rendering effects of various components inside the vehicle under different light source settings; wherein the color rendering effects include color changes, shadow distribution, and highlight effects.

[0146] Step 75: Output the color presentation effect as a vehicle interior effect image set to generate a vehicle interior color matching effect.

[0147] In the embodiment of the present application: Taking a family car as an example, first, a light source simulation environment inside the vehicle is established according to the light source data. The light source data includes parameters such as the position, brightness and color of light sources such as roof lights, reading lights, and atmosphere lights. Next, the second vehicle color matching model is imported into the light source simulation environment, and the model is rendered to preliminarily show the color matching effect. Then, the color physics algorithm is applied to simulate the illumination of the model. During the simulation process, the spectral characteristics of the light source, the reflection and absorption characteristics of the materials of various components inside the vehicle, and the visual characteristics of the human eye are considered. By calculating the reflection, refraction and absorption of light on the surface of the component, the color performance of the surface of the component is adjusted to reflect the real lighting effect. Next, the color rendering effect images of various components inside the vehicle under different light source settings are calculated and generated. These images show the color changes, shadow distribution and highlight effects of the components under different lighting conditions. Finally, the generated color rendering effect images are sorted into a vehicle interior effect image set and output.

[0148] After the vehicle interior effect and the vehicle exterior effect are output, the vehicle interior effect and the vehicle exterior effect can also be evaluated. The evaluation method includes:

[0149] B1. Establish color evaluation indicators; color evaluation indicators include color harmony, visual comfort, spatial perception and material texture.

[0150] Color evaluation index: This is a set of standard systems for quantitatively evaluating the color matching effect of vehicles, including multiple dimensions such as color harmony, visual comfort, spatial perception, and material texture performance. These indicators are designed to objectively reflect the comprehensive performance of the color matching scheme in terms of aesthetics, ergonomics, and material application.

[0151] Color harmony: Evaluate whether the color matching inside and outside the vehicle is visually harmonious and unified, and whether it follows the basic principles of color matching, such as whether the use of contrasting colors, adjacent colors, complementary colors, etc. is appropriate.

[0152] Visual comfort: examine whether the color scheme is likely to cause visual fatigue and whether it can maintain visual pleasure after long-term viewing.

[0153] Spatial perception: Evaluate the impact of color matching on the sense of space inside the vehicle. For example, light colors may make the space appear more spacious, while dark colors may bring a sense of compactness.

[0154] Material texture expression: Analyze how the color scheme is combined with the texture of the vehicle's interior and exterior materials, and whether it highlights the characteristics of the materials, such as the coolness of metal and the luxury of leather.

[0155] Based on the principles of color science and vehicle design experience, specific standards and scoring criteria for color evaluation indicators are formulated. The rationality and practicality of the indicator system are verified and adjusted through expert review and user surveys.

[0156] B2. Processing the vehicle interior and exterior effects based on a preset image analysis algorithm to extract color feature parameters; wherein the color feature parameters at least include hue, brightness, and saturation.

[0157] Image analysis algorithm: an algorithm that can automatically analyze the color information in an image and accurately extract color characteristic parameters such as hue, brightness, and saturation.

[0158] B3. Calculate the color evaluation scores of the vehicle interior effect and the vehicle exterior effect according to the color evaluation index.

[0159] Color evaluation score: It is a quantitative score obtained through certain calculation rules based on color evaluation indicators and color characteristic parameters, which is used to intuitively reflect the effect of the vehicle color scheme.

[0160] The color evaluation scores include color harmony score, visual comfort score, space perception score and material texture performance score.

[0161] Color harmony score: Scoring is based on factors such as the uniformity of hue distribution and the appropriateness of color contrast. For example, the entropy of hue distribution can be calculated to evaluate uniformity, and the number and intensity of contrasting colors can be used to evaluate the appropriateness of contrast. The final score is obtained through weighted summation, with weights determined based on expert opinions and user surveys.

[0162] Visual comfort score: Considers factors such as color softness (such as by calculating the proximity of the color to neutral colors), brightness contrast (such as calculating the average value of brightness differences in the image), etc. The final score is also obtained by weighted summation.

[0163] Spatial Perception Score: This score is calculated by analyzing the effect of color on the sense of depth and spaciousness of space. For example, bright colors generally increase the sense of space, while dark tones may reduce it. The specific score is calculated based on the matching degree of color feature parameters with the spatial perception model.

[0164] Material texture performance score: The score is obtained by comparing the color with the material texture and gloss. A machine learning model can be used to learn the relationship between color and texture by training a large amount of sample data to obtain a score.

[0165] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a color matching engineering efficiency improvement device based on a large model, and its structure is as follows Figure 2 shown.

[0166] Figure 2 A schematic diagram of a color matching engineering efficiency improvement device based on a large model provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0167] The data acquisition module is used to collect color matching data; wherein the color matching data includes vehicle color matching data and color matching data. The vehicle color matching data includes vehicle exterior color matching data and vehicle interior color matching data;

[0168] A color matching suggestion generation module is used to import vehicle data of a vehicle to be matched with color into a trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure and configuration;

[0169] A first vehicle model generation module, used for processing a vehicle model of a vehicle to be color matched based on the color matching suggestion, so as to generate a first vehicle color matching model equipped with the color matching suggestion;

[0170] A second vehicle model generation module, configured to adjust the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color blending algorithm to generate a second vehicle color matching model;

[0171] A vehicle exterior color module, used for processing a second vehicle color matching model based on a preset environment model to obtain vehicle exterior effects under different external environments;

[0172] A light source data determination module, used to determine the in-vehicle light source data based on the vehicle data; wherein the in-vehicle light source data includes the light source position, light source brightness, light source structure and light source setting;

[0173] The vehicle interior color module is used to process the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effect under different light source settings.

[0174] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0175] The devices and methods provided in the embodiments of the present application correspond one to one, and therefore, the devices also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0176] Those skilled in the art will appreciate that the embodiments of the present application may provide methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0177] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0181] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0182] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0183] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0184] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A color matching engineering efficiency improvement method based on a large model, characterized in that: The method comprises: Collecting color matching data; wherein the color matching data includes vehicle color matching data and color matching data, and the vehicle color matching data includes vehicle exterior color matching data and vehicle interior color matching data; Importing vehicle data of a vehicle to be color matched into the trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure and configuration; Processing the vehicle model of the vehicle to be color matched based on the color matching suggestion to generate a first vehicle color matching model equipped with the color matching suggestion; Adjusting and filling the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color blending algorithm to generate a second vehicle color matching model; Processing the second vehicle color matching model based on a preset environment model to obtain vehicle exterior effects under different external environments; Determining in-vehicle light source data based on the vehicle data; wherein the in-vehicle light source data includes light source position, light source brightness, light source structure, and light source setting; The second vehicle color matching model is processed based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effect under different light source settings.

2. According to the large model-based color matching engineering efficiency improvement method of claim 1, it is characterized in that: Before importing the vehicle data of the vehicle to be color matched into the trained color matching model to obtain color matching suggestions, the method further includes: Constructing a color matching model based on a preset convolutional neural network and a preset long short-term memory network; wherein the convolutional neural network is used to identify image features in the color matching data, and the long short-term memory network is used to process time sequence information in the color matching data; Cleaning and arranging the color matching data, removing outliers and noise data, to generate sample data; wherein the sample data is data in a unified format, and the sample data includes a training set, a test set, and a validation set; Training and validating the color matching model based on the sample data, and evaluating the generalization ability of the color matching model based on a preset cross-validation strategy; Optimizing the parameters of the color matching model based on a preset back propagation algorithm; When the performance of the color matching model on the validation set reaches a preset accuracy threshold, a trained color matching model is generated.

3. According to the large model-based color matching engineering efficiency improvement method of claim 1, it is characterized in that: Importing vehicle data of the vehicle to be color matched into the trained color matching model to obtain color matching suggestions, specifically including: Preprocessing the vehicle data of the vehicle to be color matched to generate input data; wherein the input data is in a format that can be recognized by the trained color matching model; Importing the input data into the trained color matching model; The color matching model outputs a color matching suggestion corresponding to the input data based on the feature information of the input data.

4. The color matching engineering efficiency improvement method based on a large model according to claim 1 is characterized in that: Processing the vehicle model of the vehicle to be color matched based on the color matching suggestion to generate a first vehicle color matching model equipped with the color matching suggestion specifically includes: Determine the color matching suggestion; wherein the color matching suggestion includes color suggestions and material suggestions for multiple components; Building a three-dimensional model of the vehicle to be color matched based on a preset three-dimensional modeling software; wherein the three-dimensional model includes a plurality of components; The color matching suggestion is matched with the three-dimensional model based on the component to generate a first vehicle color matching model; wherein, some components in the first vehicle color matching model may not be colored.

5. The color matching engineering efficiency improvement method based on a large model according to claim 4 is characterized in that: Adjusting the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color harmony algorithm to generate a second vehicle color matching model specifically includes: Processing the first vehicle color matching model and vehicle data to determine the design style and color matching tone of the vehicle to be color matched; According to the color harmony algorithm, the contrast, saturation and brightness relationship between the components in the first vehicle color matching model are calculated, and the design style and the color matching tone are referred to to identify the disharmonious factors in the first vehicle color matching model; wherein the disharmonious factors are colors that are inconsistent with the design style and the color matching tone; Removing the inharmonious factors to generate a color matching model of the vehicle to be filled; The vehicle color matching model to be filled is filled according to the design style and the color matching tone to generate a second vehicle color matching model.

6. The color matching engineering efficiency improvement method based on a large model according to claim 1 is characterized in that: Processing the second vehicle color matching model based on a preset environment model to obtain vehicle exterior effects under different exterior environments specifically includes: Construct a multi-environment simulation system; wherein the multi-environment simulation system includes multiple scenes and multiple weather conditions; importing the second vehicle color matching model into the multi-environment simulation system; The second vehicle color matching model is processed based on a preset rendering algorithm to determine the vehicle exterior effect.

7. The color matching engineering efficiency improvement method based on a large model according to claim 6 is characterized in that Processing the second vehicle color matching model based on a preset rendering algorithm to generate a vehicle exterior effect image set specifically includes: Setting rendering parameters; wherein the rendering parameters include lighting conditions, shadow effects, reflectivity, refractive index and environment map; Performing multi-angle rendering on the second vehicle color matching model to generate vehicle exterior effect images including different viewing angles; According to the preset time period and weather conditions, the lighting and weather effects in the rendering environment are adjusted to generate vehicle exterior effect images under different time periods and weather conditions.

8. The color matching engineering efficiency improvement method based on a large model according to claim 1 is characterized in that: Processing the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effect under different light source settings, specifically including: Establishing a light source simulation environment; wherein the light source simulation environment is configured according to the light source data; Importing the second vehicle color matching model into the light source simulation environment; Applying a color physics algorithm to perform illumination simulation on the second vehicle color matching model based on the spectral characteristics of the light source, the reflection and absorption characteristics of the material, and the visual characteristics of the human eye; Calculate and generate the color rendering effects of various components inside the vehicle under different light source settings; wherein the color rendering effects include color changes, shadow distribution and highlight effects; The color rendering effect is output as a vehicle interior effect image set to generate a vehicle interior color matching effect.

9. The color matching engineering efficiency improvement method based on a large model according to claim 8, characterized in that: The method further comprises: Establishing color evaluation indicators; wherein the color evaluation indicators include color harmony, visual comfort, spatial perception, and material texture performance; Processing the vehicle interior effect and the vehicle exterior effect based on a preset image analysis algorithm to extract color feature parameters; wherein the color feature parameters at least include hue, brightness, and saturation; The color evaluation scores of the vehicle interior effect and the vehicle exterior effect are calculated according to the color evaluation index.

10. A color matching engineering efficiency improvement device based on a large model, characterized in that: The device comprises: A data acquisition module, used to acquire color matching data; wherein the color matching data includes vehicle color matching data and color matching data; the vehicle color matching data includes vehicle exterior color matching data and vehicle interior color matching data; A color matching suggestion generation module is used to import vehicle data of a vehicle to be matched with color into the trained color matching model to obtain color matching suggestions; wherein the vehicle data includes at least one of the following data: vehicle model, publicity, structure and configuration; A first vehicle model generation module, used for processing the vehicle model of the vehicle to be color matched based on the color matching suggestion to generate a first vehicle color matching model equipped with the color matching suggestion; A second vehicle model generating module, configured to adjust the contrast, saturation and brightness of the colors in the first vehicle color matching model based on the vehicle data and a preset color blending algorithm to generate a second vehicle color matching model; A vehicle exterior color module, used for processing the second vehicle color matching model based on a preset environment model to obtain vehicle exterior effects under different external environments; A light source data determination module, used to determine the in-vehicle light source data based on the vehicle data; wherein the in-vehicle light source data includes the light source position, light source brightness, light source structure and light source setting; The vehicle interior color module is used to process the second vehicle color matching model based on the light source data and in combination with a preset color physics algorithm to determine the vehicle interior effect under different light source settings.

Images