Personalized customized vi design method and system

Abstract

The invention discloses a personalized customized vi design method and system, and relates to the technical field of visual identification design, the design method comprises the following specific steps: S100, data acquisition: docking with an enterprise internal management system to obtain core data, using a web crawler tool to collect Internet related information, and using the web crawler tool to store the core data; according to the method, data in multiple aspects of industry attributes, brand positioning and color preference of target audiences of an enterprise are deeply analyzed by utilizing an artificial intelligence technology, highly intelligent color analysis and recommendation are realized, and the color matching degree of the industry, the color preference of the target audiences and multiple dimensions of color coordination correction factors are comprehensively considered. According to the method, the color scheme meeting the enterprise image and the market demand can be accurately recommended to the user, the intelligent color recommendation not only improves the design efficiency, but also ensures that the color scheme is highly matched with the enterprise positioning and audience preference, and the visual impact and brand recognition degree of the design are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of visual identification design, and in particular to a personalized customized VI design method and system. Background Art

[0002] With the intensification of market competition, companies' design demands for visual identification systems (VI) are becoming increasingly diversified and personalized. As a key link in shaping the corporate image, the importance of VI design is self-evident. It not only carries the company's brand concept and cultural connotation, but also is an important medium for establishing emotional connections with target audiences and conveying brand value. Therefore, how to efficiently and accurately design a VI system that conforms to the company's characteristics and audience preferences has become an urgent problem to be solved in the current design field.

[0003] Traditional VI design methods often rely on the designer's personal experience and aesthetic concepts, and lack scientific data analysis and personalized customization. This leads to the inability to accurately grasp the target audience's color preferences and behavior patterns during the design process, thus affecting the pertinence and effectiveness of VI design. In addition, traditional methods usually ignore the importance of industry color adaptability, resulting in the designed VI works may not be consistent with the company's industry attributes, reducing the brand's professionalism and credibility. Furthermore, the user interaction link in the traditional VI design process is relatively weak, and users can often only see the final effect after the design is completed, which limits the user's participation and satisfaction in the design process. At the same time, traditional methods also have shortcomings in design generation and effect evaluation. The lack of automated design generation algorithms and comprehensive evaluation index systems makes design efficiency low and it is difficult to ensure the quality of design works.

[0004] Therefore, a personalized VI design method and system is developed to provide enterprises with more accurate and efficient VI design solutions, helping them stand out in the fierce market competition. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a personalized VI design method and system. The invention realizes the personalized customization of VI design through data collection, analysis, design recommendation, user interaction, design generation and effect evaluation. The invention first collects enterprise, audience and user behavior data, and then analyzes color preferences, user behavior patterns and emotional needs. Based on the analysis results, it recommends color and graphic schemes and incorporates emotional elements. Users can interactively select in the system interface, and finally generate and optimize VI design works. During the whole process, the design scheme is continuously evaluated to ensure that user needs are met.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, a personalized customized VI design method, the specific steps of the design method are:

[0007] S100, Data Collection: Connect with the company's internal management system to obtain core data, use web crawler tools to collect relevant information on the Internet, cooperate with market research institutions to obtain audience characteristic data, use social media platform API interfaces to obtain audience behavior and interest tag information, and use system design interface front-end technology to record user operation behavior and selection preferences in real time;

[0008] S200, Data Analysis: Clean and pre-process the collected data, remove noise and abnormal data, extract color data from the collected data, and recommend color schemes for the target audience by calculating the comprehensive color recommendation index. The formula is: CCRIF = ICF × k1 + TACPF × k2 + R c , where k1 and k2 are the coefficients for adjusting the fusion weights of industry color adaptation and target audience color preference, R c is the color coordination correction factor, ICF is the industry color adaptability, TACPF is the target audience color preference, extract user behavior data, and use the user behavior association strength formula to measure the user behavior association strength. The formula is: where N A B represents the number of times the user performs behavior A and behavior B simultaneously, N A Represents the total number of times the user performs behavior A. It finds the graphic element combinations and operation patterns that users often select at the same time. The cluster center is calculated using the user behavior pattern cluster center formula. The formula is: C j represents the center of the jth cluster, n j is the number of user behavior data samples in the jth cluster, X ij is the user behavior feature vector of the i-th sample in the j-th cluster. Users with similar behavior patterns are divided into different groups. A personalized graphic recommendation plan is customized for each group. Text data is extracted from the collected data. Sentiment analysis tools and techniques are used to analyze the content of the target audience's comments on social media. Combined with market research data, the target audience's emotional needs are quantified. Based on the results of the emotional needs analysis, emotional design elements are extracted. Taking into account the emotional needs and the influence of design elements, the brand emotional connection strength formula is used to measure the emotional connection strength between the brand and the audience. The formula is: BECIF = ENQF × k3 + EDEIF × k4 + C e , measures the emotional connection strength between the brand and the audience, k3 and k4 are the coefficients for adjusting the weight, C e It is the correction factor of the brand’s own image on the emotional connection;

[0009] S300, Design Recommendation: Based on color analysis results, it selects matching color combinations from the color library and presents them to users in a visual format. It also provides color matching principles and applicable scenarios. Based on user behavior pattern analysis, it generates graphic solutions, which are displayed as thumbnails on the design interface. Users can click to view detailed information and preview them. Based on emotional design analysis, it incorporates emotional elements into the recommended design solutions.

[0010] S400, user interaction: users can view, compare, and select recommended color and graphic schemes on the system interface with real-time feedback. They can interact with the system by entering text descriptions and uploading reference images. They can also view and adjust the VI design effects on different platforms in real time.

[0011] S500, design generation: After the user determines the final color and graphic scheme, the system automatically calls the design template and generation algorithm to generate the complete VI design work, and performs quality inspection and optimization;

[0012] S600, Effect Evaluation: Continuously evaluate the design plan at each stage of the design, generate feedback reports based on the results, point out problems and improvement directions, and users optimize the design to a satisfactory effect based on the feedback.

[0013] Furthermore, in the calculation of the comprehensive color recommendation index in the data analysis in S200, the calculation formula of the industry color adaptability ICF is: Among them, n represents the number of key features related to the enterprise industry, w i is the weight of the i-th feature, reflecting the importance of this feature in measuring the compatibility between industry and color, S i is the color adaptation score corresponding to the i-th feature, which indicates the degree of matching between the feature and a certain color scheme. The higher the score, the better the adaptability.

[0014] Furthermore, in the calculation of the comprehensive color recommendation index of the data analysis in S200, the calculation formula of the target audience color preference value TACPF is TACPF=α×CP+β×AP+γ×BP, wherein CP represents the color preference score based on age factors, AP represents the color preference score based on gender factors, BP represents the color preference score based on cultural background factors, and α, β, and γ are the fusion weights of the three factors of age, gender, and cultural background, respectively.

[0015] Furthermore, in the above S200, the matching degree is calculated by using a personalized graphic recommendation matching degree formula in the data analysis to recommend a graphic solution for the group. The formula is: Among them, m represents the number of key features of the graph, w′ i is the weight of the i-th feature, Di is the matching score between the user behavior pattern and the i-th graph feature.

[0016] Furthermore, in the data analysis of S200, the emotional needs of the target audience are quantified by using an emotional needs quantification formula, which is: Quantify emotional needs, r represents the number of categories of emotional needs of the target audience, e i is the importance weight of the i-th type of emotional needs, L i It is the quantitative value of the target audience's satisfaction degree of the i-th type of emotional needs.

[0017] Furthermore, in the data analysis of S200, the influence of the emotional design elements is evaluated by the influence formula, which is: Where s represents the number of emotional design elements, f j is the emotional transmission weight of the jth emotional design element, I j It is the quantitative value of the influence of the j-th design element on the audience's emotions in actual application.

[0018] Furthermore, the S300, color recommendation in design recommendation, obtains color schemes and related parameters suitable for the enterprise based on the results of intelligent color analysis. For industry color adaptability, it screens out color combinations with ICF values ​​higher than a specific threshold based on the results calculated according to the industry color adaptability formula. Based on the target audience color preference fusion formula, it considers the target audience's color preferences based on age, gender, and cultural background factors. According to the pre-set preference weight ranges of different audience groups, it selects color combinations that meet the characteristics of the target audience. Combined with the comprehensive color recommendation index formula, it comprehensively considers the color coordination correction factor to screen out color combinations with good visual coordination, and at the same time excludes color combinations with inharmonious problems in contrast, brightness, and saturation.

[0019] Furthermore, the S300, graphic solution recommendation in the design recommendation, generates a series of graphic solutions based on the user behavior pattern analysis results, especially the user behavior pattern mined through the user behavior association strength formula and the user behavior pattern cluster center formula, combined with the personalized graphic recommendation matching degree formula.

[0020] Furthermore, the S300 integrates and recommends emotional elements in design recommendations. Based on the analysis results of emotional design elements, information about the emotional needs of the target audience and the emotional connection between the brand and the audience is obtained from the emotional needs quantification formula, the emotional design element influence formula and the brand emotional connection strength formula. According to the emotional needs analysis, the design elements that can trigger specific emotional resonance are determined. At the same time, considering the brand's own image and positioning, emotional design elements that are consistent with the brand values ​​are screened out. For color schemes, according to the requirements of emotional design, the color hue, saturation and brightness are fine-tuned. In graphic design, emotional graphic shapes are integrated into logos, icons and other graphic elements. At the same time, emotional factors are also considered in the detailed processing of graphics to make the graphics more friendly. When recommending design schemes to users, the emotional elements integrated therein and their design intentions are pointed out.

[0021] On the other hand, a personalized VI design system is characterized in that the system includes a data acquisition module, a data analysis module, a design recommendation module, a user interaction module, a design generation module, and an effect evaluation module:

[0022] The data collection module: obtains data on the industry attributes and brand positioning of enterprises by connecting to enterprise databases, uses web crawler technology to collect enterprise-related information, and uses market research tools to collect data on the age, gender, and cultural background of target audiences; embeds code in the system design interface to record user operation behavior and selection preference data in real time during the design process;

[0023] The data analysis module: Based on the industry color database and target audience characteristic data, it uses an algorithm formula to analyze color preferences, finds the user's common graphic combinations and color preference patterns through the algorithm formula, finds the relationship between emotional characteristics and design elements based on psychological theory and big data analysis, and determines the direction of emotional design through analysis of audience emotional data;

[0024] The design recommendation module: Based on the color analysis results, it selects appropriate color schemes from the color library and presents them to the user in an intuitive manner, along with explanations of the principles and applicable scenarios. Based on the analysis of user behavior patterns, it generates a variety of graphic schemes and displays them in thumbnail form for users to choose from. In combination with emotional design analysis, it recommends VI adjustment schemes and design schemes that incorporate emotional elements in a timely manner.

[0025] The user interaction module provides a user-friendly interface to facilitate design operations. It supports in-depth interaction with the system through text descriptions and uploading reference images, and displays recommended solutions and design effects in real time. When users adjust their solutions, the system provides timely feedback.

[0026] The design generation module: after the user determines the final design plan, it automatically generates a complete VI design work based on the design template and generation algorithm, and performs quality inspection and optimization on it;

[0027] The effect evaluation module: establishes a comprehensive evaluation index system covering multiple dimensions such as visual appeal, information clarity, and brand consistency, evaluates the design plan in real time during the design process, and provides users with detailed feedback and improvement suggestions based on the evaluation results.

[0028] Compared with the existing technology, this personalized VI design method and system has the following beneficial effects:

[0029] 1. The present invention uses artificial intelligence technology to conduct in-depth analysis of various data such as the company's industry attributes, brand positioning, and target audience's color preferences, thereby achieving highly intelligent color analysis and recommendation. By comprehensively considering multiple dimensions such as industry color adaptability, target audience color preferences, and color coordination correction factors, it can accurately recommend color schemes that are in line with the company's image and market demand. This intelligent color recommendation not only improves design efficiency, but also ensures that the color scheme is highly consistent with the company's positioning and audience preferences, thereby enhancing the visual impact and brand recognition of the design.

[0030] 2. The present invention can automatically generate graphic elements that meet the user's personalized needs by comprehensively collecting data on the user's operating behavior and selection preferences during the design process. This function not only greatly improves the user's participation and satisfaction, but also makes the design works more in line with the user's actual needs and aesthetic preferences. Graphic creation based on user behavior patterns not only taps into the user's potential needs, but also provides users with a variety of graphic choices through algorithm optimization and personalized recommendations. This user-centered graphic creation method not only improves the level of personalization and differentiation of the design, but also promotes in-depth interaction and real-time feedback between users and the design system, and promotes the continuous optimization and improvement of design works.

[0031] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0033] Figure 1 Design a flowchart for a customized VI system;

[0034] Figure 2 A flowchart of a personalized VI design method. DETAILED DESCRIPTION

[0035] The following is a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] Example 1:

[0037] VI design for fashion brands

[0038] Company Background and Target Audience: A fashion brand specializes in fashionable apparel for young women. Its goal is to create a vibrant, stylish, and unique brand image to attract female consumers aged 18-30 who pursue fashion trends and value individual expression. The brand emphasizes the values ​​of innovation, freedom, and self-confidence. Its product range includes casual wear and formal wear, with diverse styles that blend international fashion elements with local cultural characteristics.

[0039] Data collection phase: Connect with the company's internal customer relationship management system and inventory management system to obtain information on customer purchase records, preferred styles, product sales trends and inventory turnover rates; use web crawler tools to collect information on fashion trends, hot topics, and competitive product images from fashion-related platforms to analyze industry dynamics; cooperate with professional institutions to conduct various forms of surveys to collect information on young female consumers' perceptions of fashion brands, preferred colors and graphic styles, and consumption habits; and use the social media platform API interface to obtain target audience behavior data, embed code in the brand's online design tools and offline store experience areas, record user design operation behaviors such as style and color selection, pattern combination, and dwell time on design elements, and also record users' preferences for collecting, sharing, and purchasing intentions for design solutions.

[0040] Data analysis phase:

[0041] Intelligent color analysis: Build a fashion industry color database, collect case studies of many successful fashion brands, analyze the color combinations used in different series, seasons, and marketing campaigns, and identify key features related to the fashion industry, such as seasonal trends and fashion styles. Suppose the number of key features related to the fashion industry is n, and assign a corresponding weight w to each feature. iBased on the target audience survey data, we analyze the color preference scores of young women. For example, pink and blue are highly preferred in this group. The color preference score based on age factors is set as CP, and the color preference score based on cultural background factors is set as BP. Since gender has a certain influence on color preferences in the fashion industry, the color preference score based on gender factors is set as AP. The fusion weights of age, gender, and cultural background are α, β, and γ respectively. The industry color adaptability is calculated using the following formula: The target audience's color preference is calculated as follows: TACPF = α × CP + β × AP + γ × BP, combined with the color coordination correction factor R c , the comprehensive color recommendation index is obtained, the formula is: CCRIF=ICF×k1+TACPF×k2+R c According to the comprehensive color recommendation index, a color combination of high brightness and low saturation pink and light blue is recommended, which can not only reflect the sense of fashion but also meet the preference of young women for fresh colors, while ensuring that the color matching is visually coordinated and comfortable, such as pink and white for casual wear, and light blue and gold for dress design.

[0042] User behavior pattern analysis: The collected user behavior data is cleaned and preprocessed to remove abnormal operations and noise data. The association rule mining algorithm is used to find the clothing styles and color matching patterns that users often choose at the same time. For example, when choosing a simple dress, it is often paired with light-colored flat shoes and a simple shoulder bag. The cluster analysis algorithm is used to divide users into different groups according to their operation behavior characteristics. Let the number of times a user performs behavior A and behavior B at the same time be N. A B, the total number of times the user performs behavior A is N A , the user behavior association strength is measured by the user behavior association strength formula, the formula is: Assume that the number of user behavior data samples in the jth cluster in the cluster analysis is n j , the user behavior feature vector of the i-th sample in the j-th cluster is X ij , the cluster center is calculated by the user behavior pattern cluster center formula, the formula is: For example, for the “creative user” group, after cluster analysis, we get n j =30, user behavior feature vector X ij The cluster center C is calculated based on the features of preference for complex patterns and depth of participation in personalized customization. j , represents the typical behavior pattern of the group. The matching degree is calculated through the personalized graphic recommendation matching formula to recommend a graphic solution for the group. The formula is: For example, we recommend clothing styles with innovative patterns and unique cuts to "creative users", and simple, classic and versatile design elements to "conservative users".

[0043] Emotional design element analysis: Use sentiment analysis tools to analyze the target audience's comments on fashion brands on social media. Combined with market research data, quantify the target audience's emotional needs. Assume that the number of categories of target audience emotional needs is r, such as confidence, happiness, and uniqueness. The importance weight of the i-th category of emotional needs is e. i , the target audience's satisfaction degree of the i-th emotional demand is quantitatively expressed as L i ,Through the emotional demand quantification formula, the emotional demand is quantified according to the emotional demand analysis results. The formula is: Extract design elements related to these emotions, such as the flying bird pattern that symbolizes freedom and individuality, the rainbow element that represents vitality and happiness, and the lace that embodies quality and exquisiteness. Let the number of emotional design elements be s, and the emotional transmission weight of the jth emotional design element be f. j The quantitative value of the influence of the j-th design element on the audience's emotions in actual application is I j , the influence of emotional design elements is evaluated through the influence formula, the formula is: The brand emotional connection strength formula is used to measure the emotional connection strength between the brand and the audience. The formula is: BECIF=ENQF×k3+EDEIF×k4+C e , ensure that design elements are consistent with brand values, reasonably integrate emotional elements into the design, and enhance the emotional bond between the brand and consumers.

[0044] Design recommendation stage:

[0045] Color recommendation: Based on the color analysis results, color combinations suitable for the spring series are screened from the color library and visually presented to the user in the form of color palettes on the design tool interface. For example, a color palette with pink and light blue as the main colors and white and gold as the secondary colors is displayed. At the same time, the color matching principles are explained. For example, the combination of pink and light blue can create a fresh and sweet atmosphere, which is suitable for casual wear in spring and summer; the addition of white and gold can enhance the overall sense of fashion and quality, which is suitable for dress design. The applicability of these color combinations in different scenarios is explained.

[0046] Graphic scheme recommendation: Graphic schemes generated based on user behavior pattern analysis are displayed in the design interface in thumbnail form. For example, thumbnails of clothing styles with unique patterns are displayed to "creative users", and design schemes with classic patterns are displayed to "conservative users". Users can click on thumbnails to view detailed information, including high-definition images of the clothing style, design details, customizable options, and an explanation of the association between the scheme and the user's behavior pattern, such as "Based on your previous preference for simple dresses, this slim dress with simple stripes is recommended for you. You can adjust the stripe color and width according to your preference." Users can also preview the actual effect of the graphic scheme on a virtual model to experience the overall matching and wearing effect of the clothing.

[0047] Incorporate and recommend emotional elements: Incorporate emotional elements into recommended design solutions, such as adding embroidery and prints of flying bird patterns to the casual wear series, and using lace to decorate the neckline and hem of the dress series. Clearly point out these emotional elements and their design intentions in the design description, such as "The flying bird pattern symbolizes freedom and individuality, adding agility and vitality to your leisure time" and "Lace represents elegance and sophistication, allowing you to show your unique charm on important occasions." Through case studies, show how other brands have successfully used similar emotional elements to enhance their brand image and connect with consumers emotionally, guiding users to understand and accept the importance of emotional design in fashion brand VI design.

[0048] User interaction stage: Users view and compare different color and graphic schemes in the design tool interface, and the system provides real-time feedback on the effects of user operations. For example, when a user selects a color scheme to apply to a clothing style, the system immediately displays a preview of the clothing, showing the actual presentation of the color combination. Users can interact deeply with the system by entering text descriptions and uploading reference pictures. The system adjusts the recommended scheme based on user input and provides design options that better meet user needs. Users can also view the simulated display of VI design effects on different platforms in real time, and adjust the design scheme according to the characteristics and needs of different platforms, such as optimizing image size and display effects for mobile online stores to ensure that the design can attract the target audience on each platform.

[0049] Design generation stage: After the user determines the final color, graphic scheme and emotional elements, the system automatically calls the design template and generation algorithm to generate a complete VI design work, including clothing style design drawings, promotional posters, brand logos, and packaging designs. During the generation process, quality inspection and optimization are carried out to ensure the clarity and precision of the graphics, the accuracy and consistency of the colors, and the clarity and readability of the text descriptions. For example, the clothing style design drawings are optimized in detail to ensure smooth cutting lines and clear pattern printing; the promotional posters are color calibrated to ensure consistent display effects on different devices; and the brand logo is improved in clarity so that it can be clearly identified even in small-size application scenarios.

[0050] Effect evaluation stage: At each stage of the design, the effect evaluation module continuously evaluates the design plan, analyzes the user's visual focus and browsing path when viewing the design plan through eye tracking technology, evaluates visual appeal, evaluates the clarity of information communication through user testing and semantic analysis, and evaluates brand consistency by comparing the degree of fit between the design plan and the brand positioning and values. For example, if it is found that when viewing the promotional poster, the user's eyes are more focused on the model and ignore the brand logo and important promotional information, the system will prompt to adjust the poster layout to highlight key information. A detailed feedback report will be generated based on the evaluation results, pointing out the problems and improvement directions in the design. The user will optimize the design based on the feedback until a satisfactory effect is achieved, ensuring that the final VI design can effectively convey the brand image, attract the target audience, and enhance the brand's market competitiveness.

[0051] In this embodiment, a personalized customized VI design method builds a unique image for a fashion brand. Data collection is multi-source and comprehensive, providing a rich basis for subsequent analysis. Intelligent color analysis uses relevant formulas to integrate industry and audience factors to determine the color combination that fits the spring series. User behavior pattern analysis uses algorithm formulas to mine and classify user behavior patterns and customize personalized graphic solutions. Emotional design element analysis extracts and incorporates emotional elements based on formulas. Design recommendations present solutions intuitively. User interaction achieves efficient communication. Design generation ensures the quality of the work. Effect evaluation continuously improves. This method enables fashion brand VI design to accurately meet audience needs and enhance brand competitiveness.

[0052] Example 2:

[0053] VI design for technology companies

[0054] Company Background and Target Audience: A technology company specializes in artificial intelligence and is committed to developing innovative intelligent technology solutions. It primarily provides services to enterprise-level clients, targeting decision makers, technical experts, and R&D personnel in the technology industry who value technological expertise, professionalism, innovation, and data security. The company's core values ​​emphasize intelligent drive, innovation leadership, and reliability. Its products include artificial intelligence algorithms, data analysis platforms, and intelligent solutions.

[0055] Data collection phase: Connect with the company's internal R&D, customer service, and financial systems to obtain information on technology R&D direction, customer needs, profitability, patented technologies, and team size; use web crawlers to collect technology trends, competitive landscapes, and policy and regulatory information in the field of artificial intelligence from news websites, forums, and academic platforms to analyze industry conditions; cooperate with professional institutions to conduct questionnaires, interviews, and seminars with enterprise-level customers to collect professionals' awareness of technology brands, technology expectations, preferred colors and graphic elements, and purchasing considerations; use social media platform API interfaces to obtain target audience behavior data to analyze their areas of interest and influence; embed code in the company's relevant platforms to record user operation behaviors and selection preferences, such as attention time, operation frequency, viewing time, and download intentions.

[0056] Data analysis phase:

[0057] Intelligent color analysis: Build a color database for the technology industry, collect case studies of numerous successful technology companies, analyze the color combinations they use in brand logos, product interfaces, and promotional materials, and identify key characteristics related to the technology industry, such as technological innovation and data security. Assume that the number of key characteristics related to the technology industry is n, and assign a corresponding weight w to each characteristic. i Based on the target audience survey data, we analyze the color preference scores of professionals in the technology industry. We set the color preference score based on industry professional needs as CP, and the color preference score based on data security symbolism as BP. Since different corporate styles in the technology industry have a certain impact on color preferences, we set the color preference score based on corporate style factors as AP. The fusion weights of age, gender, and cultural background are α, β, and γ respectively. The industry color compatibility is calculated using the following formula: The target audience's color preference is calculated as follows: TACPF = α × CP + β × AP + γ × BP, combined with the color coordination correction factor. The comprehensive color recommendation index is obtained, the formula is: CCRIF=ICF×k1+TACPF×k2+R c .

[0058] User behavior pattern analysis: Clean and pre-process the collected user behavior data, remove invalid operations and interference data, and use association rule mining algorithms to discover the technical modules and functional combination patterns that users often pay attention to at the same time. Suppose the number of times a user performs behavior A and behavior B at the same time is N. AB , the total number of times the user performs behavior A is N A , the user behavior association strength formula is used to measure the user behavior association strength. The formula is: Users are divided into different groups according to their operational behavior characteristics. Suppose the number of user behavior data samples in the jth cluster in the cluster analysis is n j , the user behavior feature vector of the i-th sample in the j-th cluster is X ij , the cluster center is calculated by the user behavior pattern cluster center formula, the formula is: For example, for the “Technology Exploration Users” group, after cluster analysis, we get n j =40, calculate the cluster center C j , represents the typical behavior pattern of the group. The matching degree is calculated through the personalized graphic recommendation matching formula to recommend a graphic solution for the group. The formula is: For example, we recommend interface designs with more complex data visualization charts and innovative graphic elements for "technology exploration users", and recommend concise, easy-to-operate function icons and reasonably laid out interface designs for "practical users".

[0059] Emotional design element analysis: Use sentiment analysis tools to analyze the target audience's comments on technology brands on social media. Combined with market research data, quantify the target audience's emotional needs. Assume that the number of categories of target audience emotional needs is r, such as reliable, efficient, and intelligent. The importance weight of the i-th category of emotional needs is e. i The quantitative value of the target audience's satisfaction degree of the i-th emotional need is L i , emotional needs are quantified through the emotional needs quantification formula, the formula is: Based on the results of the emotional needs analysis, we extract design elements related to these emotions, such as dynamic lines representing intelligence and innovation, shield icons symbolizing data security, and simple arrows representing efficiency. Let the number of emotional design elements be s, and the emotional transmission weight of the jth emotional design element be f. j The quantitative value of the influence of the j-th design element on the audience's emotions in actual application is I j , the influence of emotional design elements is evaluated through the influence formula, the formula is: The brand emotional connection strength formula is used to measure the emotional connection strength between the brand and the audience. The formula is: BECIF=ENQF×k3+EDEIF×k4+C e, ensure that design elements are consistent with brand values, reasonably incorporate emotional elements into the design, and enhance the trust and loyalty of the brand and customers.

[0060] Design recommendation stage:

[0061] Color recommendation: Based on the results of color analysis, select color combinations suitable for technology companies from the color library and present them visually to users in the form of color palettes on technology display platforms and product design interfaces. For example, display a set of color palettes with dark blue, silver gray and green as the main colors, and provide an explanation of the color matching principles. For example, the combination of dark blue and silver gray can create a sense of technology and high-end quality, which is suitable for the main colors of brand logos and product interfaces; green embellishments can highlight innovation and vitality elements, and can be used in the color design of prompt information and interactive elements. Explain the applicability of these color combinations in different products and scenarios. For example, the interface design with dark blue as the main color is suitable for data analysis platforms, giving people a professional and calm feeling; the packaging design with silver gray as the main color can enhance the product's sense of technology and modernity, and is suitable for the appearance packaging of hardware products.

[0062] Graphical solution recommendations: Graphical solutions generated based on user behavior pattern analysis are displayed in the design interface in thumbnail form. For example, thumbnails of interface designs with complex data visualization charts and innovative graphic elements are displayed to "technology exploration users", and simple and intuitive functional icons and rationally laid out interface design solutions are displayed to "practical users". Users can click on thumbnails to view detailed information, including high-definition screenshots of the interface design, introductions to functional modules, interactive operation demonstrations, and descriptions of the association between the solution and user behavior patterns, such as "Based on your previous frequent use of data analysis functions, we recommend this interface design with powerful data visualization functions. You can quickly switch between different analysis views by clicking on the icon." Users can also preview the actual operational effects of the graphical solution on simulated devices to experience the product's ease of use and functionality.

[0063] Integration and recommendation of emotional elements: Incorporate emotional elements into recommended design solutions, such as adding dynamic line elements to product promotional videos, using shield icons on the cover of technical documents, and using simple arrows in the operation guides of the user interface. Clearly point out these emotional elements and their design intentions in the design description, such as "dynamic line elements represent the intelligence and innovation of our products, showing you the flow and processing of data", "shield icons symbolize our strict protection of data security, so you can use our products with confidence". Through cases, show other technology companies that have successfully used similar emotional elements to enhance their brand image and customer trust, and guide users to understand and accept the importance of emotional design in the VI design of technology companies.

[0064] User interaction stage: Users view and compare different color and graphic schemes on the technology display platform and product design interface, and the system provides real-time feedback on the effects of user operations. For example, when a user selects a color scheme to apply to the product interface, the system immediately displays a preview of the interface, demonstrating the impact of color matching on visual comfort and information readability. Users can interact deeply with the system by entering text descriptions and uploading reference images. The system adjusts the recommended scheme based on user input and provides design options that better meet user needs. Users can also view the simulated display of VI design effects on different platforms in real time and adjust the design scheme according to the characteristics of different platforms and audience needs.

[0065] Design generation stage: After the user determines the final color, graphic scheme and emotional elements, the system automatically calls the design template and generation algorithm to generate a complete VI design work, including software product interface design, promotional posters, technical document layout, and brand logo. During the generation process, quality inspection and optimization are carried out to ensure the clarity and precision of the graphics, the accuracy and consistency of the colors, and the clarity and readability of the text descriptions. For example, the software product interface design is optimized in detail to ensure that the icons are clearly identifiable and the interface layout is reasonable. The promotional posters are color calibrated to ensure consistent display effects on different devices; the clarity of the brand logo is improved so that it can be clearly identified even in small-size application scenarios.

[0066] Effect evaluation stage: At each stage of the design, the effect evaluation module continuously evaluates the design plan, analyzes the user's visual focus and browsing path when viewing the design plan through eye tracking technology, evaluates visual appeal, evaluates the clarity of information communication through user testing and semantic analysis, and evaluates brand consistency by comparing the degree of fit between the design plan and the brand positioning and values. For example, if it is found that when viewing the promotional poster, the user's eyes are more focused on the product picture and ignore the brand logo and important technical advantages, the system will prompt to adjust the poster layout and highlight key information. A detailed feedback report will be generated based on the evaluation results, pointing out the problems and improvement directions in the design. The user will optimize the design based on the feedback until a satisfactory effect is achieved, ensuring that the final VI design can effectively convey the brand image, attract the target audience, and enhance the brand's market competitiveness.

[0067] In this embodiment, the personalized customized VI design method is successfully applied in technology companies. The data collection is comprehensive and in-depth, which helps to grasp the company and industry situation. Intelligent color analysis selects color combinations that reflect the sense of technology based on formulas. User behavior pattern analysis relies on algorithmic formulas to explore user behavior patterns. Graphic solutions are customized by grouping. Emotional design element analysis incorporates appropriate elements based on formulas. Design recommendation, user interaction, design generation and effect evaluation are closely coordinated to optimize the design. This method helps technology companies create VI designs that meet their positioning and enhance their market competitiveness.

[0068] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A personalized VI design method, characterized in that: The specific steps of this design method are: S100, data collection: connect with the internal management system of the enterprise to obtain core data, use web crawler tools to collect Internet related information, cooperate with market research institutions to obtain audience characteristic data, use social media platform API interface to obtain audience behavior and interest tag information, and record user operation behavior and selection preferences in real time through system design interface front-end technology; S200, data analysis: clean and preprocess the collected data, remove noise and abnormal data, extract color data from the collected data, and recommend color schemes for the target audience by calculating the comprehensive color recommendation index. The formula is: CCRIF = ICF × k1 + TACPF × k2 + R c , where k1 and k2 are the coefficients for adjusting the fusion weights of industry color matching and target audience color preference, R c is the color coordination correction factor, ICF is the industry color adaptability, TACPF is the target audience color preference, extract user behavior data, and use the user behavior association strength formula to measure the user behavior association strength. The formula is: Where N A B represents the number of times the user performs behavior A and behavior B at the same time, N A Indicates the total number of times the user performs behavior A, finds the graphic element combinations and operation modes that users often select at the same time, and uses the user behavior pattern cluster center formula to calculate the cluster center, which is: C j represents the center of the jth cluster, n j is the number of user behavior data samples in the jth cluster, X ij is the user behavior feature vector of the i-th sample in the j-th cluster. Users with similar behavior patterns are divided into different groups. A personalized graphic recommendation plan is customized for each group. Text data from the collected data is extracted. Sentiment analysis tools and techniques are used to analyze the content of the target audience's comments on social media. Combined with market research data, the target audience's emotional needs are quantified. Based on the results of the emotional needs analysis, emotional design elements are extracted. The emotional needs and the influence of design elements are comprehensively considered. The emotional connection strength between the brand and the audience is measured through the brand emotional connection strength formula. The formula is: BECIF=ENQF×k3+EDEIF×k4+C e , which measures the strength of the emotional connection between the brand and the audience. k3 and k4 are the coefficients for adjusting the weights. C e It is the correction factor of the brand’s own image on the emotional connection; S300, design recommendation: based on the color analysis results, it selects the qualified color combinations from the color library and presents them to the user in a visual way. At the same time, it also provides the color matching principle and applicable scene description. It generates graphic solutions based on the analysis of user behavior patterns and displays them as thumbnails on the design interface. Users can click to view detailed information and preview. Based on the emotional design analysis, it incorporates emotional elements into the recommended design solutions. S400, user interaction: users can view, compare and select recommended color and graphic schemes on the system interface, with real-time feedback function. Users can interact with the system by entering text descriptions and uploading reference pictures, and can view and adjust the simulation display of VI design effects on different platforms in real time; S500, design generation: After the user determines the final color and graphic scheme, the design template and generation algorithm are automatically called to generate a complete VI design work, and quality inspection and optimization are performed; S600, effect evaluation: continuously evaluate the design plan at each design stage, generate feedback reports based on the results, point out problems and improvement directions, and users optimize the design to a satisfactory effect based on the feedback.

2. A personalized VI design method according to claim 1, characterized in that: In the calculation of the comprehensive color recommendation index of the data analysis in S200, the calculation formula of the industry color matching degree ICF is: Where n represents the number of key features related to the enterprise industry, w i is the weight of the i-th feature, reflecting the importance of this feature in measuring the compatibility between industry and color, S i is the color adaptation score corresponding to the i-th feature, indicating the degree of matching between the feature and a certain color scheme. The higher the score, the better the adaptability.

3. A personalized VI design method according to claim 1, characterized in that: In the calculation of the comprehensive color recommendation index of the data analysis in S200, the calculation formula of the target audience color preference value TACPF is TACPF=α×CP+β×AP+γ×BP, wherein CP represents the color preference score based on age factors, AP represents the color preference score based on gender factors, BP represents the color preference score based on cultural background factors, and α, β, and γ are the fusion weights of the three factors of age, gender, and cultural background, respectively.

4. A personalized VI design method according to claim 1, characterized in that: In the above S200, the matching degree is calculated by using the personalized graphic recommendation matching degree formula in the data analysis to recommend a graphic solution for the group. The formula is: Among them, m represents the number of key features of the graph, w′ i is the weight of the i-th feature, D i is the matching score between the user behavior pattern and the i-th graph feature.

5. A personalized VI design method according to claim 1, characterized in that: In the S200, the emotional needs of the target audience are quantified by using an emotional needs quantification formula in the data analysis, and the formula is: Quantify emotional needs, r represents the number of categories of emotional needs of the target audience, e i is the importance weight of the i-th type of emotional needs, L i It is the quantitative value of the degree to which the target audience satisfies the i-th type of emotional needs.

6. A personalized VI design method according to claim 1, characterized in that: In the data analysis of S200, the influence of emotional design elements is evaluated by the influence formula of emotional design elements, and the formula is: Where s represents the number of emotional design elements, f j is the emotional transmission weight of the jth emotional design element, I j It is the quantitative value of the influence of the j-th design element on the audience's emotions in practical applications.

7. A personalized VI design method according to claim 1, characterized in that: The S300, color recommendation in design recommendation, obtains color schemes and related parameters suitable for the enterprise based on the results of intelligent color analysis. For industry color adaptability, the color combinations with ICF values ​​higher than a specific threshold are screened out based on the results calculated according to the industry color adaptability formula. Based on the target audience color preference fusion formula, the color preferences of the target audience based on age, gender, and cultural background factors are considered. According to the pre-set preference weight ranges of different audience groups, the color combinations that meet the characteristics of the target audience are selected. Combined with the comprehensive color recommendation index formula, the color coordination correction factor is comprehensively considered to screen out color combinations with good visual coordination, and at the same time, color combinations with inharmonious contrast, brightness, and saturation are excluded.

8. A personalized VI design method according to claim 1, characterized in that: The S300, graphic scheme recommendation in design recommendation, generates a series of graphic schemes according to the user behavior pattern analysis results, especially the user behavior pattern mined by the user behavior association strength formula and the user behavior pattern cluster center formula, combined with the personalized graphic recommendation matching degree formula.

9. A personalized VI design method according to claim 1, characterized in that: The S300, incorporation and recommendation of emotional elements in design recommendation, obtains information about the emotional needs of the target audience and the emotional connection between the brand and the audience from the emotional needs quantification formula, the emotional design element influence formula and the brand emotional connection strength formula based on the analysis results of the emotional design elements. According to the emotional needs analysis, the design elements that can trigger specific emotional resonance are determined. At the same time, considering the brand's own image and positioning, the emotional design elements that are consistent with the brand's values ​​are screened out. For the color scheme, according to the requirements of emotional design, the color hue, saturation and brightness are fine-tuned. In terms of graphic design, emotional graphic shapes are integrated into logos, icons and other graphic elements. At the same time, in the detailed processing of the graphics, emotional factors are also considered to make the graphics more friendly. When recommending a design scheme to a user, the emotional elements integrated therein and their design intentions are pointed out.

10. A personalized VI design system according to any one of claims 1 to 9, characterized in that: The system includes a data acquisition module, a data analysis module, a design recommendation module, a user interaction module, a design generation module and an effect evaluation module: The data collection module: obtains data on the industry attributes and brand positioning of enterprises by connecting with enterprise databases, collects enterprise-related information using web crawler technology, and uses market research tools to collect data on the age, gender, and cultural background of target audiences; Embed code in the system design interface to record user operation behavior and selection preference data in real time during the design process; The data analysis module: based on the industry color database and target audience characteristic data, uses algorithm formulas to analyze color preferences, finds out the user's common graphic combinations and color preference patterns through the algorithm formula, finds out the relationship between emotional characteristics and design elements based on psychological theory and big data analysis, and determines the emotional design direction through analysis of audience emotional data; The design recommendation module: based on the color analysis results, selects appropriate color schemes from the color library, presents them to the user in an intuitive manner, and attaches explanations of the principles and applicable scenarios; generates diversified graphic schemes based on user behavior pattern analysis, and displays them in the form of thumbnails for users to choose; combines emotional design analysis, and recommends VI adjustment schemes and design schemes that incorporate emotional elements in a timely manner; The user interaction module provides a user-friendly interface to facilitate design operations, supports users to interact deeply with the system through text descriptions and uploading reference pictures, displays recommended solutions and design effects in real time, and provides timely system updates and feedback when users adjust solutions; The design generation module: after the user determines the final design plan, the complete VI design work is automatically generated according to the design template and generation algorithm, and the quality is checked and optimized; The effect evaluation module: establishes a comprehensive evaluation index system covering multiple dimensions of visual appeal, information communication clarity, and brand consistency, evaluates the design plan in real time during the design process, and provides users with detailed feedback and improvement suggestions based on the evaluation results.

Images