Image design visual communication system and method based on big data

Abstract

The invention discloses an image design visual communication system and method based on big data, and relates to the technical field of image design visual communication systems.The method comprises the steps that massive image data are analyzed and screened through the data mining technology, and an image sample set is obtained; classifying and clustering the image sample set by adopting a machine learning algorithm, identifying common visual styles and modes, and obtaining a visual style template; based on the visual style template, target audience preferences are analyzed through a user behavior data analysis method, visual style template design is optimized, and a personalized customized visual design scheme is obtained; creating a virtual environment and displaying the design scheme based on a personalized customized visual design scheme in combination with an augmented reality (AR) technology so as to simulate an actual application scene and obtain a visual communication scheme; and a social media monitoring tool is adopted to track and analyze the public reaction of the visual communication scheme after actual release, and the visual communication effect is evaluated according to public interaction data.

Description

Technical Field

[0001] The present invention relates to the technical field of image design visual communication systems, and in particular to an image design visual communication system and method based on big data. Background Art

[0002] An image design visual communication system is an integrated solution that aims to deeply process and analyze image data through a series of advanced technical means, so as to generate a personalized visual design solution that not only conforms to a specific visual style template but also meets the preferences of the target audience.

[0003] In the technical field of image design visual communication systems, in the face of a vast amount of image data, traditional methods are difficult to efficiently screen and analyze, and traditional design solutions often ignore the personalized needs of users, resulting in a mismatch between the design solution and user preferences. At the same time, in the existing technology, there is a lack of an effective public response tracking mechanism for the released visual communication solutions, making it difficult to comprehensively evaluate their market performance. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an image design visual communication method based on big data to solve the problems that in the face of a vast amount of image data, traditional methods are difficult to efficiently screen and analyze, and traditional design solutions often ignore the personalized needs of users, resulting in a mismatch between the design solution and user preferences.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an image design visual communication method based on big data, which includes:

[0008] Analyzing and screening a vast amount of image data by using data mining technology to obtain an image sample set;

[0009] Classifying and clustering the image sample set by using machine learning algorithms to identify common visual styles and patterns, and obtaining a visual style template;

[0010] Based on the visual style template, analyzing the preferences of the target audience by using user behavior data analysis methods, and optimizing the design of the visual style template to obtain a personalized customized visual design solution;

[0011] Based on the personalized customized visual design solution, creating a virtual environment and displaying the design solution by combining with augmented reality (AR) technology to simulate the actual application scenario, and obtaining a visual communication solution;

[0012] Use social media monitoring tools to track and analyze the public response to the visual communication plan after its actual release, evaluate the visual communication effect based on public interaction data, and obtain the visual communication evaluation results;

[0013] Improve the image design workflow based on the visual communication evaluation results to obtain an optimized visual communication plan.

[0014] As a preferred solution of the big data-based image design visual communication method described in the present invention, wherein: the analysis and screening of a large amount of image data by using data mining technology to obtain an image sample set specifically includes the following steps:

[0015] Use a data mining method based on cluster analysis to collect data to obtain an original image data set;

[0016] Preprocess the original image data set;

[0017] The preprocessing includes removing noise, adjusting the size, and unifying the format to obtain a preprocessed image data set;

[0018] Select color histograms and texture features as the main features, and extract the feature vector F(i j ) from the preprocessed image data set;

[0019] Use the K-means clustering algorithm to classify the feature vector F(i j ), and each image is assigned to the nearest cluster center point according to the feature vector F(i j ) to form a clustering result;

[0020] Select the image with the smallest distance from the cluster center point from multiple clusters as the sample of this category, and obtain the image sample set S.

[0021] As a preferred solution of the big data-based image design visual communication method described in the present invention, wherein: the classification and clustering of the image sample set by using a machine learning algorithm to identify common visual styles and patterns to obtain a visual style template specifically includes the following steps:

[0022] Use the pre-trained convolutional neural network model ResNet50 to perform deep feature extraction on each image in the image sample set S to obtain the feature vector after deep extraction;

[0023] Use the principal component analysis method PCA to perform dimensionality reduction processing on the feature vector after deep extraction to obtain the feature vector after dimensionality reduction

[0024] Use the hierarchical clustering algorithm to perform cluster analysis on the feature vector after dimensionality reduction ;

[0025] Calculate the center point C of category q l , that is, the average feature vector of category q l , namely category q l ; of the average feature vector

[0026] Take the center point C of category q l as the visual style template of category q l as the visual style template of category q l .

[0027] As a preferred solution of the visual communication method for image design based on big data according to the present invention, wherein: based on the visual style template, analyze the preferences of the target audience through the user behavior data analysis method, and optimize the visual style template design to obtain a personalized customized visual design solution. The specific steps are as follows:

[0028] Collect user behavior data related to the target audience;

[0029] The user behavior data includes browsing history, click-through rate, and purchase records;

[0030] Analyze the user behavior data and calculate the preference feature vector of the user using the collaborative filtering algorithm;

[0031] Map the preference feature vector P(u i ) of the user to the feature space of the visual style template to obtain the mapped preference feature vector;

[0032] According to the mapped user preference feature vector M(P(u i ))), adjust the visual style template C l , and obtain the optimized visual style template;

[0033] Based on the optimized visual style template T′(C l ), generate a personalized customized visual design solution D.

[0034] As a preferred solution of the visual communication method for image design based on big data according to the present invention, wherein: based on the personalized customized visual design solution, combine the augmented reality AR technology to create a virtual environment and display the design solution to simulate the actual application scenario to obtain the visual communication solution. The specific steps are as follows:

[0035] According to the requirements of the target application scenario, use 3D modeling software to create a virtual environment model;

[0036] Import the personalized customized visual design solution D into the virtual environment model;

[0037] Use the augmented reality technology AR to combine the virtual environment and the imported visual design solution D for an augmented reality experience, and the user can view and interact through the AR device;

[0038] The AR devices include smartphones, tablets and AR glasses;

[0039] In the augmented reality experience, the target audience is invited to conduct user experience tests;

[0040] Based on the results and feedback data of the user experience test, the visual design plan D is optimized and adjusted, and a visual communication plan is generated.

[0041] As a preferred solution of the method for visual communication of image design based on big data according to the present invention, wherein: the social media monitoring tool is used to track and analyze the public reaction after the actual release of the visual communication plan, and the visual communication effect is evaluated according to the public interaction data to obtain the visual communication evaluation result. The specific steps are as follows:

[0042] The visual communication plan is released to multiple social media platforms, and the multiple social media platforms include Weibo, WeChat and Instagram;

[0043] The social media monitoring tool Hootsuite is used to collect the interaction data of the public on the released visual communication plan, and the interaction data includes the number of likes, comments, shares and user feedback;

[0044] The collected interaction data is cleaned and preprocessed to remove noise and irrelevant data, and the processed interaction data D s ′;

[0045] Based on the processed interaction data D s ′, calculate the key interaction index I to quantify the effect of the visual communication plan;

[0046] Perform sentiment analysis on the comment content of users to judge whether the public's attitude towards the visual communication plan is positive, negative or neutral, and obtain the sentiment analysis result;

[0047] Based on the interaction index I and the sentiment analysis result E a , generate the final visual communication evaluation result R.

[0048] As a preferred solution of the method for visual communication of image design based on big data according to the present invention, wherein: the visual communication evaluation result is used to improve the image design work process to obtain an optimized visual communication plan. The specific steps are as follows:

[0049] Conduct in-depth analysis on the visual communication evaluation result R, extract the success factors, and obtain the analysis result;

[0050] According to the analysis result, identify the specific improvement points in the current design process;

[0051] The improvement points include specific requirements in user feedback, weak links in interaction metrics, and negative emotions in sentiment analysis;

[0052] According to the identified improvement points, adjust the parameters in the image design workflow;

[0053] The parameters in the image design workflow include the weight matrix and the learning rate;

[0054] Use the adjusted parameters to regenerate a personalized visual design plan;

[0055] And import the regenerated visual design plan into the virtual environment, and create an optimized augmented reality experience through augmented reality technology AR;

[0056] Based on the optimized augmented reality experience, collect new public interaction data to calculate new interaction metrics, and obtain an optimized visual communication plan according to the new interaction metrics and sentiment analysis results.

[0057] In a second aspect, the present invention provides an image design visual communication system based on big data, including:

[0058] A data mining module, a machine learning module, a user behavior analysis module, an augmented reality module, a social media monitoring module, and an optimization and improvement module;

[0059] The data mining module is used to analyze and screen a large amount of image data by using data mining technology to obtain an image sample set;

[0060] The machine learning module is used to classify and cluster the image sample set by using machine learning algorithms to identify common visual styles and patterns and obtain a visual style template;

[0061] The user behavior analysis module is used to analyze the preferences of the target audience based on the visual style template through user behavior data analysis methods, and optimize the visual style template design to obtain a personalized visual design plan;

[0062] The augmented reality module is used to create a virtual environment and display the design plan based on the personalized visual design plan in combination with augmented reality technology to simulate the actual application scenario and obtain a visual communication plan;

[0063] The social media monitoring module is used to track and analyze the public response to the visual communication plan after actual release by using social media monitoring tools, evaluate the visual communication effect according to the public interaction data, and obtain a visual communication evaluation result;

[0064] The optimization and improvement module is used to improve the image design workflow based on the visual communication evaluation results to obtain an optimized visual communication plan.

[0065] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the method for visual communication of image design based on big data as described in the first aspect of the present invention is implemented.

[0066] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the method for visual communication of image design based on big data as described in the first aspect of the present invention is implemented.

[0067] The beneficial effects of the present invention are as follows: By using data mining technology to analyze and screen a large amount of image data, an image sample set is obtained. Through precise sample selection, the efficiency and accuracy of subsequent design work are improved. Not only unnecessary waste of computing resources is reduced, but also it is ensured that the selected samples can fully reflect the diversity of the target visual style. Based on the visual style template, the preferences of the target audience are analyzed through the user behavior data analysis method, and the visual style template design is optimized to obtain a personalized customized visual design plan. By deeply understanding user preferences, the present invention can create a highly personalized visual design plan, significantly improving user satisfaction and participation, thereby enhancing the brand image and market competitiveness. Based on the personalized customized visual design plan, combined with the augmented reality (AR) technology, a virtual environment is created and the design plan is displayed to simulate the actual application scenario to obtain a visual communication plan. Through the augmented reality technology, the present invention can discover potential problems at an early stage and correct them in time, avoiding the cost increase caused by large-scale modification in the later stage. At the same time, it also provides an intuitive experience platform for users, enhancing the interactivity and immersion. Description of the Drawings

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0069] Figure 1 It is a flowchart of the method for visual communication of image design based on big data in Embodiment 1.

[0070] Figure 2 It is a schematic diagram of the system for visual communication of image design based on big data in Embodiment 1. Detailed Embodiments

[0071] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification.

[0072] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0073] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0074] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a visual communication method for image design based on big data, including the following steps:

[0075] S1. Analyze and screen a large amount of image data by using data mining technology to obtain an image sample set;

[0076] Furthermore, use a data mining method based on cluster analysis to collect data to obtain an original image data set;

[0077] Preprocess the original image data set;

[0078] The preprocessing includes removing noise, adjusting the size, and unifying the format to obtain a preprocessed image data set;

[0079] Select color histograms and texture features as the main features, and extract feature vectors F(i j ) from the preprocessed image data set. The expression is:

[0080] F(i j ) = [H(i j ), T(i j )];

[0081] Among them, H(i j ) is the color histogram feature, and T(i j ) is the texture feature;

[0082] Use the K-means clustering algorithm to classify the feature vectors F(i j ). Each image is classified according to the feature vector F(i j) It is assigned to the nearest cluster center point to form a clustering result;

[0083] Select the image with the smallest distance from the cluster center point from multiple clusters as the sample of this category, and obtain the image sample set S;

[0084] It should be noted that by using data mining technology to analyze and screen massive image data, this step can not only efficiently process large-scale data sets, but also ensure that the finally selected image sample set is representative. The method can significantly reduce the amount of data for subsequent processing, improve the calculation efficiency, and at the same time ensure that the selected samples can accurately reflect the diversity of the target visual style, providing a solid foundation for subsequent design optimization.

[0085] S2. Use machine learning algorithms to classify and cluster the image sample set, identify common visual styles and patterns, and obtain visual style templates;

[0086] Further, use the pre-trained convolutional neural network model ResNet50 to perform deep feature extraction on each image in the image sample set S to obtain the feature vectors after deep extraction;

[0087] Use the principal component analysis method PCA to perform dimensionality reduction processing on the feature vectors after deep extraction to obtain the feature vectors after dimensionality reduction The expression is:

[0088]

[0089] Among them, PCA(x) represents applying principal component analysis to the input vector x and outputting the vector after dimensionality reduction;

[0090] Use the hierarchical clustering algorithm for the feature vectors after dimensionality reduction to perform clustering analysis;

[0091] Calculate the center point C l of category q l , that is, the average feature vector of category q l , and the expression is:

[0092]

[0093] Among them, |q l | represents the number of images in category q l , is the feature vector after dimensionality reduction;

[0094] Take the center point C l of category q l as the visual style template of category q l ;

[0095] It should be noted that by using machine learning algorithms to classify and cluster the image sample set, not only can common visual styles and patterns be identified, but also potential design trends can be discovered. By using the pre-trained convolutional neural network model ResNet50 to extract deep features and performing PCA dimensionality reduction processing, the computational complexity can be effectively reduced, and the clustering effect can be improved. The application of the hierarchical clustering algorithm further improves the accuracy of classification, making the generated visual style template more suitable for the actual application scenario and enhancing the flexibility and adaptability of the design.

[0096] S3. Based on the visual style template, analyze the preferences of the target audience through the user behavior data analysis method, and optimize the design of the visual style template to obtain a personalized customized visual design solution;

[0097] Furthermore, collect user behavior data related to the target audience;

[0098] The user behavior data includes browsing history, click-through rate, and purchase records;

[0099] Analyze the user behavior data, and use the collaborative filtering algorithm to calculate the preference feature vector of the user, and the expression is:

[0100] P(u i ) = CF(U, u i );

[0101] Among them, CF(U, u i ) represents the output result of applying the collaborative filtering algorithm to the user data set U and the specific user u i , that is, the preference feature vector of the user u i , and P(u i ) is the preference feature vector of the user u i ;

[0102] Map the preference feature vector P(u i ) of the user to the feature space of the visual style template to obtain the mapped preference feature vector;

[0103] According to the mapped user preference feature vector M(P(u i )) to adjust the visual style template C l , and obtain the optimized visual style template, and the expression is:

[0104]

[0105] Among them, α is the learning rate, which is used to control the step size of each adjustment, represents the sum of the differences between all user preference feature vectors and the current template;

[0106] Based on the optimized visual style template T′(Cl ) to generate a personalized visual design solution D;

[0107] It should be noted that based on the visual style template, the preferences of the target audience are analyzed through the user behavior data analysis method. The process can accurately capture the personalized needs and preferences of users. The application of the collaborative filtering algorithm not only improves the calculation accuracy of user preferences, but also provides a scientific basis for designers, enabling them to dynamically adjust the design solution according to user feedback. This personalized customization method not only improves the user experience, but also enhances the market competitiveness of the brand, promoting the wide acceptance and use of products.

[0108] S4. Based on the personalized visual design solution, combine the augmented reality (AR) technology to create a virtual environment and display the design solution to simulate the actual application scenario, and obtain the visual communication solution;

[0109] Furthermore, according to the requirements of the target application scenario, use 3D modeling software to create a virtual environment model;

[0110] Import the personalized visual design solution D into the virtual environment model;

[0111] Use the augmented reality (AR) technology to combine the virtual environment and the imported visual design solution D for the augmented reality experience, and users can view and interact through AR devices;

[0112] The AR devices include smartphones, tablets, and AR glasses;

[0113] In the augmented reality experience, invite the target audience to conduct user experience tests;

[0114] Based on the results and feedback data of the user experience test, optimize and adjust the visual design solution D, and generate the visual communication solution;

[0115] It should be noted that combining the augmented reality (AR) technology to create a virtual environment and display the design solution can test and verify the actual effect of the design solution in a near-real application scenario. This method not only allows designers to discover potential problems in the early stage and correct them in time, avoiding the cost increase caused by large-scale modifications in the later stage, but also provides an intuitive experience platform for users, enhancing the interactivity and immersion. In addition, optimizing and adjusting the design solution based on the results and feedback data of the user experience test can ensure the practicality and user satisfaction of the final solution.

[0116] S5. Use social media monitoring tools to track and analyze the public response after the actual release of the visual communication solution, evaluate the visual communication effect according to the public interaction data, and obtain the visual communication evaluation result;

[0117] Furthermore, publish the visual communication plan to multiple social media platforms, including Weibo, WeChat, and Instagram;

[0118] Use the social media monitoring tool Hootsuite to collect the interaction data of the public on the published visual communication plan, including the number of likes, comments, shares, and user feedback;

[0119] Clean and preprocess the collected interaction data, remove noise and irrelevant data, and obtain the processed interaction data D s ′;

[0120] Based on the processed interaction data D s ′, calculate the key interaction indicator I to quantify the effect of the visual communication plan, and the expression is:

[0121] I = ComputeMetrics(D s ′);

[0122] Among them, ComputeMetrics(D s ′) represents the process of calculating the key interaction indicator from the processed data D s ′;

[0123] Conduct sentiment analysis on the comment content of users to judge whether the public's attitude towards the visual communication plan is positive, negative, or neutral, and obtain the sentiment analysis result, and the expression is:

[0124] E a = SentimentAnalysis(D s ′);

[0125] Among them, SentimentAnalysis(D s ′) represents the process of conducting sentiment analysis on the input data D s ′;

[0126] Based on the interaction indicator I and the sentiment analysis result E a , generate the final visual communication evaluation result R, and the expression is:

[0127] R = GenerateReport(I, E a );

[0128] Among them, GenerateReport(I, E a ) represents the process of generating an evaluation report according to the interaction indicator I and the sentiment analysis result E a ;

[0129] It should be noted that by using social media monitoring tools to track and analyze the public's reaction to the visual communication plan after its actual release, the real feedback from the public can be obtained in real time, which is crucial for evaluating the effectiveness of the design plan. By collecting interaction data such as the number of likes, comments, and shares, and combining sentiment analysis, the public's attitudes and emotional tendencies can be comprehensively understood. This not only helps to quantify the success of the design plan but also provides specific directions and bases for subsequent design improvements, thus achieving continuous optimization.

[0130] S6. Use the visual communication evaluation results to improve the image design workflow and obtain an optimized visual communication plan.

[0131] Furthermore, conduct an in-depth analysis of the visual communication evaluation result R, extract the success factors, and obtain the analysis result.

[0132] Based on the analysis result, identify the specific improvement points in the current design process.

[0133] The improvement points include specific requirements in user feedback, weak links in interaction metrics, and negative emotions in sentiment analysis.

[0134] According to the identified improvement points, adjust the parameters in the image design workflow.

[0135] The parameters in the image design workflow include the weight matrix and the learning rate.

[0136] Use the adjusted parameters to regenerate a personalized visual design plan.

[0137] And import the regenerated visual design plan into the virtual environment, and create an optimized augmented reality experience through augmented reality technology AR.

[0138] Based on the optimized augmented reality experience, collect new public interaction data to calculate new interaction metrics, and obtain an optimized visual communication plan according to the new interaction metrics and sentiment analysis results.

[0139] It should be noted that using the visual communication evaluation results to improve the image design workflow can form a closed-loop feedback system to ensure the continuous optimization of the design process. By conducting an in-depth analysis of the success factors and identifying the specific improvement points in the current design process, designers can flexibly adjust parameter settings according to the actual situation, such as the weight matrix and the learning rate. This method not only improves the accuracy and efficiency of the design but also ensures that the design plan always meets the market demand and user expectations, thus achieving long-term and stable product updates and development.

[0140] This embodiment also provides an image design visual communication system based on big data, including:

[0141] A data mining module, a machine learning module, a user behavior analysis module, an augmented reality module, a social media monitoring module, and an optimization and improvement module;

[0142] The data mining module is used to analyze and screen a large amount of image data by adopting data mining techniques to obtain an image sample set;

[0143] The machine learning module is used to classify and cluster the image sample set by adopting machine learning algorithms, identify common visual styles and patterns, and obtain a visual style template;

[0144] The user behavior analysis module is used to analyze the preferences of the target audience based on the visual style template through user behavior data analysis methods, and optimize the visual style template design to obtain a personalized customized visual design plan;

[0145] The augmented reality module is used to create a virtual environment and display the design plan based on the personalized customized visual design plan in combination with augmented reality technology to simulate the actual application scenario and obtain a visual communication plan;

[0146] The social media monitoring module is used to track and analyze the public reaction after the actual release of the visual communication plan by adopting social media monitoring tools, evaluate the visual communication effect according to the public interaction data, and obtain a visual communication evaluation result;

[0147] The optimization and improvement module is used to improve the image design work process with the visual communication evaluation result to obtain an optimized visual communication plan.

[0148] This embodiment also provides a computer device applicable to the case of the visual communication method for image design based on big data, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the visual communication method for image design based on big data as proposed in the above embodiment.

[0149] The computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through Wi-Fi, carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0150] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for visual communication of image design based on big data proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0151] In summary, the present invention analyzes and screens a large amount of image data by using data mining technology to obtain an image sample set. Through precise sample selection, the efficiency and accuracy of subsequent design work are improved. It not only reduces unnecessary waste of computing resources but also ensures that the selected samples can fully reflect the diversity of the target visual style. Based on the visual style template, the preferences of the target audience are analyzed by using the user behavior data analysis method, and the visual style template design is optimized to obtain a personalized customized visual design solution. By deeply understanding user preferences, the present invention can create a highly personalized visual design solution, significantly improving user satisfaction and engagement, thereby enhancing the brand image and market competitiveness. Based on the personalized customized visual design solution, a virtual environment is created and the design solution is displayed by combining the augmented reality (AR) technology to simulate the actual application scenario, obtaining a visual communication solution. Through the augmented reality technology, the present invention can discover potential problems at an early stage and correct them in a timely manner, avoiding the cost increase caused by large-scale modifications in the later stage. At the same time, it also provides an intuitive experience platform for users, enhancing the interactivity and immersion.

[0152] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A visual communication method for image design based on big data, characterized in that: Including: By adopting data mining technology to analyze and screen massive image data, an image sample set is obtained; Using machine learning algorithms to classify and cluster the image sample set, identifying common visual styles and patterns, and obtaining a visual style template; Based on the visual style template, analyzing the preferences of the target audience through user behavior data analysis methods, and optimizing the visual style template design to obtain a personalized visual design solution; Based on the personalized visual design solution, combining augmented reality (AR) technology to create a virtual environment and display the design solution to simulate the actual application scenario, and obtaining a visual communication solution; Using social media monitoring tools to track and analyze the public reaction after the actual release of the visual communication solution, evaluating the visual communication effect according to the public interaction data, and obtaining a visual communication evaluation result; Based on the visual communication evaluation result, improving the image design work process to obtain an optimized visual communication solution.

2. The visual communication method for image design based on big data according to claim 1, wherein: The specific steps for obtaining the image sample set by adopting data mining technology to analyze and screen massive image data are as follows: Using a data mining method based on cluster analysis to collect data, obtaining an original image data set; Preprocessing the original image data set; The preprocessing includes removing noise, adjusting the size, and unifying the format to obtain a preprocessed image data set; Select the color histogram and texture features as the main features, and extract the feature vector F(i j ) from the preprocessed image dataset; Use the K-means clustering algorithm to classify the feature vector F(i j ). Each image is assigned to the nearest cluster center according to the feature vector F(i j ) to form a clustering result; Selecting the image with the smallest distance from the cluster center point from multiple clusters as the sample of this category, and obtaining the image sample set S.

3. The visual communication method for image design based on big data according to claim 2, characterized in that: The specific steps for using machine learning algorithms to classify and cluster the image sample set, identifying common visual styles and patterns, and obtaining a visual style template are as follows: Using the pre-trained convolutional neural network model ResNet50 to perform deep feature extraction on each image in the image sample set S to obtain a feature vector after deep extraction; The principal component analysis method PCA is used to reduce the dimension of the feature vectors after deep extraction, and the feature vectors after dimension reduction are obtained Use the hierarchical clustering algorithm to perform clustering analysis on the feature vectors after dimensionality reduction ; Calculate the center point C of class q l , that is, the average feature vector of class q l , which is the average feature vector of class q l . Take the center point C of category q l as the visual style template of category q l Take the center point C of category q l as the visual style template of category q 4. The method for visual communication of image design based on big data according to claim 3, wherein: The specific steps for analyzing the preferences of the target audience through user behavior data analysis methods based on the visual style template and optimizing the visual style template design to obtain a personalized visual design solution are as follows: Collecting user behavior data related to the target audience; The user behavior data includes browsing history, click-through rate, and purchase records; Analyzing the user behavior data and using a collaborative filtering algorithm to calculate the preference feature vector of the user; Map the user's preference feature vector P(u i ) to the feature space of the visual style template to obtain the mapped preference feature vector; According to the mapped user preference feature vector M(P(u i ))), adjust the visual style template C l and obtain the optimized visual style template; Based on the optimized visual style template T ′ (C l ) to generate a personalized visual design solution D.

5. The visual communication method for image design based on big data according to claim 4, characterized in that: The specific steps for combining augmented reality (AR) technology based on the personalized visual design solution to create a virtual environment and display the design solution to simulate the actual application scenario and obtain a visual communication solution are as follows: According to the requirements of the target application scenario, using 3D modeling software to create a virtual environment model; Importing the personalized visual design solution D into the virtual environment model; Using augmented reality (AR) technology to combine the virtual environment and the imported visual design solution D for an augmented reality experience, and the user views and interacts through an AR device; The AR device includes a smart phone, a tablet computer, and AR glasses; Inviting the target audience to conduct a user experience test in the augmented reality experience; Based on the results and feedback data of the user experience test, optimizing and adjusting the visual design solution D, and generating a visual communication solution.

6. The visual communication method for image design based on big data according to claim 5, wherein: Track and analyze the public response to the visual communication plan after its actual release using social media monitoring tools, evaluate the visual communication effect based on public interaction data, and obtain the visual communication evaluation result. The specific steps are as follows: Release the visual communication plan to multiple social media platforms, where the multiple social media platforms include Weibo, WeChat, and Instagram; Use the social media monitoring tool Hootsuite to collect the interaction data of the public on the released visual communication plan, where the interaction data includes the number of likes, comments, shares, and user feedback; Clean and preprocess the collected interaction data to remove noise and irrelevant data, and obtain the processed interaction data D s ′ ; Based on the processed interaction data D s ′ , calculate the key interaction metric I to quantify the effect of the visual communication plan; Conduct sentiment analysis on the content of the user comments to judge whether the public's attitude towards the visual communication plan is positive, negative, or neutral, and obtain the sentiment analysis result; Based on the interaction metric I and the sentiment analysis result E a , generate the final visual communication evaluation result R.

7. The visual communication method for image design based on big data according to claim 6, characterized in that: The steps for improving the image design workflow based on the visual communication evaluation result to obtain an optimized visual communication plan are as follows: Conduct an in-depth analysis of the visual communication evaluation result R, extract the success factors, and obtain the analysis result; Based on the analysis result, identify the specific improvement points in the current design workflow; The improvement points include specific requirements in user feedback, weak links in interaction metrics, and negative emotions in sentiment analysis; According to the identified improvement points, adjust the parameters in the image design workflow; The parameters in the image design workflow include the weight matrix and the learning rate; Use the adjusted parameters to regenerate a personalized visual design plan; And import the regenerated visual design plan into a virtual environment, and create an optimized augmented reality experience through augmented reality technology AR; Based on the optimized augmented reality experience, collect new public interaction data to calculate new interaction metrics, and obtain an optimized visual communication plan according to the new interaction metrics and sentiment analysis result.

8. An image design visual communication system based on big data, based on the method for image design visual communication based on big data according to any one of claims 1 to 7, characterized in that: Including: A data mining module, a machine learning module, a user behavior analysis module, an augmented reality module, a social media monitoring module, and an optimization and improvement module; The data mining module is used to analyze and screen massive image data by adopting data mining technology to obtain an image sample set; The machine learning module is used to classify and cluster the image sample set by adopting machine learning algorithms to identify common visual styles and patterns, and obtain a visual style template; The user behavior analysis module is used to analyze the preferences of the target audience based on the visual style template through user behavior data analysis methods, and optimize the design of the visual style template to obtain a personalized visual design plan; The augmented reality module is used to create a virtual environment and display the design plan based on the personalized visual design plan in combination with augmented reality technology to simulate the actual application scenario, and obtain a visual communication plan; The social media monitoring module is used to track and analyze the public response to the visual communication plan after its actual release by adopting social media monitoring tools, evaluate the visual communication effect based on public interaction data, and obtain the visual communication evaluation result; The optimization and improvement module is used to improve the image design workflow based on the visual communication evaluation result to obtain an optimized visual communication plan.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the method for visual communication of image design based on big data according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for visual communication of image design based on big data according to any one of claims 1 to 7 are implemented.

Images