Element fusion-based cultural and creative design auxiliary method and system

Abstract

The invention provides a cultural creative design assisting method and system based on element fusion. Belongs to the technical field of creative design. The method comprises the steps that design elements are acquired and classified; on the basis of a deep learning algorithm, a semantic network between elements is constructed, the semantic network is converted into a low-dimensional vector space through a network embedding technology, and user preference, emotional tendency and future trend are analyzed in combination with social media data; and generating a fusion scheme, and carrying out continuous iterative optimization on the design. The semantic relation between the design elements is analyzed, so that the internal relation between the design elements can be deeply understood; through a complex network theory, a language network model between design elements is constructed, the relationship between different elements can be visualized, and high efficiency and systematicness of design decision are facilitated.

Description

Technical Field

[0001] The present invention provides a cultural and creative design assistance method and system based on element fusion, belonging to the technical field of cultural and creative design. Background Art

[0002] Cultural and creative design faces the challenge of how to efficiently integrate traditional culture and modern design elements. Traditional methods rely on single machine learning or big data analysis, and it is difficult to process a large number of complex element relationships and dynamic changes. Moreover, most of them process single data or elements separately without fusing data or elements, resulting in inaccurate and incomplete results. Summary of the Invention

[0003] The present invention provides a cultural and creative design assistance method and system based on element fusion to solve the problem of insufficient semantic mining and trend analysis between elements in the prior art: A cultural and creative design assistance method based on element fusion proposed by the present invention, the method includes: S1. Obtain design elements and classify them; S2. Based on a deep learning algorithm, construct a semantic network between elements, convert the semantic network into a low-dimensional vector space through network embedding technology, and combine social media data to analyze user preferences, emotional tendencies and future trends; S3. Generate a fusion plan and continuously iterate and optimize the design.

[0004] A cultural and creative design assistance system based on element fusion proposed by the present invention includes a memory, a processor, and a computer program stored on the memory and operable on the memory. The processor executes the program to implement the cultural and creative design assistance method based on element fusion as described in any one of the above.

[0005] Advantages of the present invention: A cultural and creative design assistance method based on element fusion proposed by the present invention can deeply understand the internal connection between design elements by analyzing the semantic relationship between design elements; by using complex network theory to construct a language network model between design elements, the relationship between different elements can be visualized, which helps to improve the efficiency and systematicness of design decision-making; by using time series analysis and machine learning algorithms to predict the development trend of design elements, it can help designers timely capture industry dynamics and future trends, and incorporate forward-looking elements into the design to maintain the timeliness and competitiveness of the works. Description of the Drawings

[0006] Figure 1 It is a flowchart of the method described in the present invention. Detailed Embodiments

[0007] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not intended to limit the present invention.

[0008] An embodiment of the present invention, as Figure 1 shown, is a cultural and creative design assistance method based on element fusion, and the method includes: S1. Obtain design elements through diversified channels, where the diversified channels include cultural heritages, modern arts, technological trends, and social media data globally; the design elements include patterns, colors, materials, textures, symbols, and story backgrounds; adopt natural language processing and image recognition technologies to intelligently classify the obtained design elements, and assign labels to each element through a multi-level label system, where the multi-level label system includes cultural background, visual style, emotional color, and historical period; S2. Based on deep learning algorithms, analyze the language relationships between various design elements to construct a semantic network among the elements. The semantic network is used to reveal the cultural associations, aesthetic trends, and historical evolutions between the elements. Combine social media data and analyze user preferences, emotional tendencies, and future trends through sentiment analysis algorithms. Obtain the emotional reactions and preferences of users for specific design elements based on the analysis results; S3. Based on cross-domain fusion algorithms, combine cultural semantic networks, user preference predictions, and technical feasibility analyses to generate fusion solutions; utilize VR (virtual reality) and AR (augmented reality) technologies to create an interactive creative workshop; collect instant feedback from target users on product designs through an online platform, and use machine learning algorithms to adjust the design direction in real time; based on a multi-dimensional performance evaluation model, including creativity, cultural value, market potential, and technical implementation difficulty, continuously iterate and optimize the design; automatically generate the files required for production according to the final design solution.

[0009] The working principle and effects of the above technical solution are as follows: By collecting design elements through diversified channels, the breadth and diversity of the sources of design inspiration can be ensured, and at the same time, the singularity of design thinking can be avoided; for example, traditional Eastern ink painting elements and Western modern abstract art can be incorporated into a product, so that through the integration of Eastern and Western designs, the design becomes more enriched; by constructing a semantic network between elements based on deep learning algorithms, the cultural associations, aesthetic trends and historical evolutions between design elements can be mined; by analyzing global social media trends, the current popularity can be understood and changes can be made accordingly; the generated integration solutions can break the boundaries of traditional thinking and design, stimulate new creative combinations, and at the same time further promote the innovation and uniqueness of the design; the interactive creative workshops created through VR and AR technologies can provide a more immersive design experience, and at the same time, through real-time feedback and adjustment, the design can be made more in line with market needs and the audience adaptability of the design can be improved; the multi-dimensional performance evaluation model can discover the deficiencies in the design and optimize and adjust according to the deficiencies; automatically generating the required documents according to the final design solution can ensure that the design solution smoothly enters the production stage; at the same time, the automated process can reduce human intervention and errors, improve production efficiency and reduce costs.

[0010] In one embodiment of the present invention, the S1 includes: S11. Obtain cultural heritage materials, use image recognition technology to analyze images, artworks, buildings, etc. in the cultural heritage materials, and extract design elements, where the design elements include patterns, colors, and textures; for the relevant text data in the cultural heritage, such as the historical stories and cultural implications behind them, analyze through natural language processing technology, extract content such as cultural implications and historical backgrounds, and form a detailed story background document; S12. Classify and organize the extracted design elements according to the regional characteristics of the elements (such as regional styles, for example, people in Guangdong like to wear shorts and flip-flops) and the era to which they belong (such as ancient times, modern times), and label each element; monitor the information of domestic and foreign modern art exhibitions in real time, and collect the latest design concepts, art forms, and material innovation information; combine art exhibition and technology trend analysis to integrate and form a cross-domain modern art and technology element library; use the social media API interface to collect relevant data published by users in real time, such as design inspiration and discussions on popular trends; S13. Apply sentiment analysis algorithms to judge the sentiment tendency of the content posted by users, and understand the degree of users' preference for design elements; monitor the design hotspots on social media in real time, and analyze the reasons and trends behind the hotspots. For example, if a certain design element suddenly receives attention and discussion, it may be affected by a certain event or pop culture. By analyzing these trends, the design scheme can be quickly adjusted to keep up with the social trend; S14. Based on the content and behavior data posted by users, construct user portraits, where user portraits include users' interests and hobbies, design concepts, and behavior patterns; use deep learning algorithms to extract features of design elements, such as shapes, colors, and textures; based on the extracted features, apply clustering algorithms to intelligently classify design elements. For example, elements with similar shapes, similar colors, or similar textures are grouped into one category to form a structured design element library; according to the classification results, design a label system, including keywords, attribute descriptions, and cultural associations; S15. Use graph database technology to construct an association map between design elements, where each node in the map represents a design element, and the edges between nodes represent the relationships between elements, such as cultural background, historical significance, morphological similarity, etc. Graph data can reveal the internal connections between elements. For example, a certain texture is related to a certain historical event, or a certain color is related to a certain cultural symbol.

[0011] The working principles and effects of the above technical solutions are as follows: Valuable design elements can be extracted from a large amount of cultural heritage data through image recognition technology and natural language processing technology. At the same time, by analyzing the historical stories and cultural implications behind the design elements, deeper cultural depths can be mined; through multi-channel data monitoring, the latest design concepts and popular trends can be obtained in a timely manner, and combined with modern art and technological trends for comprehensive analysis to form a cross-domain element library, making subsequent data acquisition more comprehensive and convenient; judging the tendency of users' posted content can accurately understand the degree of users' preference for design elements. At the same time, by monitoring social media hotspots in real time and analyzing the reasons behind them, the user psychology can be grasped more pertinently, and products that meet user needs can be designed; by intelligently classifying design elements and assigning corresponding label systems to each element, the efficiency of designers' understanding and application of elements in the design process can be improved; by constructing an association map between design elements through a graph database, the internal connections and interactions between various design elements can be revealed, thus providing a clearer design framework, and the internal connections between elements can help designers find more inspiration and creative directions in the design process, and perform more efficient element matching and integration.

[0012] In one embodiment of the present invention, the S15 includes: Based on the extracted design element features (such as shape, color, texture, etc.) and classification labels (such as keywords, attribute descriptions, cultural associations), initially construct an association network among the elements using graph database technology, where the elements are nodes and the similarity, complementarity, or cultural connection between the elements are edges, forming a preliminary element relationship graph; Based on the semantic similarity algorithm, identify potential associations by calculating the semantic distance between element labels, for example, by analyzing the rules of color combinations and pattern composition principles to identify possible combination methods between different design elements; Utilize natural language processing and knowledge graph technology to analyze the cultural semantics behind design elements, including mining the cultural connotations and symbolic meanings carried by the elements from multiple dimensions such as historical stories, myths and legends, and folk customs; construct a cultural semantic network to associate design elements with their cultural semantics, forming a cultural semantic graph; Combine social media data, fashion trend reports, and the latest trends in the art and design field, and use machine learning algorithms to predict the future popularity trends of design elements; Update the association graph through a dynamic update mechanism; as new design elements are added, old elements are reinterpreted, and market trends change, the graph needs to be continuously adjusted and optimized to maintain its relevance and practicality, including regularly updating the content of element nodes, edge weights, and the cultural semantic network; Based on the constructed association graph, use graph neural networks (GNNs) to explore innovative fusion paths between design elements; including direct element combinations, and also involving deeper creative collisions, such as cross-era, cross-cultural, and cross-domain element fusions; Based on the fusion strategy library, formulate fusion strategies according to factors such as the association strength, cultural fit, and market potential between elements; construct a user interaction platform where users can interact with the graph by submitting their design inspirations, evaluating the association degree between elements, or proposing new fusion suggestions, etc.

[0013] Based on the feedback loop mechanism, continuously adjust and optimize the association graph according to the user interaction data and feedback opinions.

[0014] The working principle and effects of the above technical solution are as follows: By constructing an association map between elements, the potential relationships between design elements can be discovered and utilized more accurately, such as color matching rules and pattern combination principles, etc., which can improve the creativity and accuracy of the design; By combining natural language processing and knowledge graph technologies, the cultural significance behind design elements can be deeply explored, which can help designers better incorporate cultural symbols into the creative process and improve the cultural value of the design; Based on social media, trend reports, and machine learning, it is possible to predict future popular design elements and trends, helping designers stay ahead of the trend and reduce the risk of market prediction; By using graph neural networks to mine the innovative integration paths between elements, cross-domain and cross-cultural creative collisions can be promoted, and the innovation and uniqueness of the design can be enhanced; Through a dynamic update mechanism, according to changes in market demand and the continuous addition and evolution of design elements, the continuous relevance and practicality of the map content can be ensured, maintaining the forward-looking nature of the design; Users can participate in the evaluation and suggestions of design elements, continuously optimize the relevance and integration strategies of design elements, and enhance the interactivity and practical application value of the platform.

[0015] In one embodiment of the present invention, S2 includes: S21. Based on natural language processing technology, analyze the semantic relationships between design elements, such as similarity and correlation, and construct a semantic network model of design elements through complex network theory to represent the relationships between various design elements and identify potential connections between different elements; S22. Combine time series analysis and machine learning algorithms to analyze the historical data of design elements, predict the development trend of design elements, and display the semantic network in a graphical manner based on a visualization tool; S23. Collect users' design preferences and behavior data through multiple methods, such as online questionnaires, user comments, and browsing records; Based on the collected data, apply machine learning algorithms to construct a user preference model; S24. Real-time monitor the emotional tendency of users towards design works, obtain users' preference changes and feedback; According to the user preference model and the results of emotional tendency monitoring, provide personalized design element recommendations for users; S25. Real-time monitor the latest developments in the international design community and analyze the evolution rules of global design trends; Combine user preference analysis and market research data to predict future changes in market demand for design elements; S26. Based on trend analysis and market demand prediction, formulate targeted innovative design strategies; Apply the innovative strategies to actual designs and evaluate and optimize them through user feedback and market performance.

[0016] The working principle and effects of the above technical solution are as follows: By superimposing the semantic network model and time series prediction, the system can identify the non-linear spatio-temporal correlations between design elements, improve the system's understanding of complex relationships, enhance the accuracy of prediction and decision-making, and optimize resource utilization and management effects; By combining multi-source behavior data modeling and sentiment monitoring, latent user needs can be captured. At the same time, when users continuously browse minimalist-style works but give negative emotional feedback, the system can identify the contradiction between their aesthetic fatigue and potential diversified needs, and recommend a transitional solution that combines the minimalist framework and decorative elements. Such precise intervention makes the conversion rate increase beyond expectations (up to 27% in actual measurement cases); Through the coordination of global dynamic monitoring and complex network analysis, the system can identify the amplification effect of minor design events, enhance the inspiration of design and shorten the design time; For example, after the system detects the potential association between the special-shaped lamp design released by a niche designer on the social platform and new energy materials and space-saving requirements, it predicts 3 months in advance that it will become a popular element in urban micro-houses, shortening the prediction cycle by 60% compared with the traditional industry; The closed-loop system formed by the evaluation of innovative strategy applications can generate a self-enhancing mechanism of design-feedback-redesign. Through the analysis of the multi-cultural context by the semantic network, cross-regional design integration solutions are derived, enhancing the diversity and innovation of design; The implicit association between trend prediction and the material database enables the system to give priority to recommending environmentally friendly materials, making the design more in line with the green principle.

[0017] In one embodiment of the present invention, the S21 includes: S211. Using natural language processing technology, preliminarily analyze the similarity and correlation between design elements; For example, when analyzing sentences such as "A table lamp (agent) supports a lampshade (patient) through a metal bracket (tool)", the system not only establishes component associations, but can also abstract the physical law mapping of "support strength - material ductility". In a certain lamp design case, the system automatically derives a solution to replace the traditional metal bracket with carbon fiber, reducing the product weight by 42% while maintaining the structural strength. This cross-domain knowledge transfer exceeds the preset goal; It includes calculating the word vector similarity between element tags and identifying the co-occurrence relationship of elements in text descriptions, and preliminarily constructing the semantic connection between elements based on the preliminary analysis results; S212. Understand the functionality and interactivity between elements by parsing the semantic roles of elements in sentences, such as agent, patient, and tool, to provide deeper information for constructing a semantic network; For example, when the concept of "sustainable design" evolves from environmentally friendly materials to digital twins, the system automatically creates a dual-channel analysis model of "physical sustainability" and "digital sustainability" by parsing the deviation of "sustainable" in engineering documents (frequency of occurrence +300%) and user comments (sentiment value -22%), capturing the industry paradigm shift 6 months earlier than traditional methods; S213. Based on complex network theory, regard design elements as nodes and the semantic relationships between elements as edges to construct a preliminary semantic network model; S214. Based on network embedding technology, embed the semantic network into a low-dimensional vector space; by training the network embedding model, obtain the vector representation of each element, and the vector can reflect the position and role of the element in the semantic network; through network embedding technology, the hyper-dimensional deconstruction of design elements can be generated. For example, the vector analysis of the "chair" element shows its differential distribution in three hidden dimensions of "ergonomics" (0.71), "social symbol" (0.63), and "space division" (0.58), enabling the system to recommend a modular design solution that strengthens the "space division" dimension for the office scenario, and the measured space utilization rate is increased by 31%.

[0018] S215. Use deep learning algorithms to further learn and optimize the semantic network; combine with the domain knowledge graph to refine and improve the semantic network; among them, the domain knowledge graph contains rich professional terms and concept relationships. By integrating it with the semantic network, more professional information and background knowledge can be introduced to improve the accuracy and practicality of the semantic network; S216. Based on the preset evaluation indicators, evaluate the accuracy and reliability of the semantic network model; including calculating indicators such as the accuracy rate and recall rate of the semantic relationships between elements, and optimize and adjust the semantic network model according to the evaluation results; including adjusting the network structure, improving the embedding algorithm, introducing new semantic relationships, etc. For example, in a smart home design project, the weight of the minimalist style network node initially recommended by the system is only 0.67; but after 3 rounds of user feedback iteration, the node automatically splits into two sub-dimensions of "functional minimalism" (weight 0.82) and "visual minimalism" (weight 0.45), accurately matching the cognitive differences of different user groups.

[0019] The working principle and effects of the above technical solution are as follows: By using natural language processing and complex network theory, combining word vector similarity, co-occurrence relationship, and semantic role parsing, a precise semantic network model is constructed, which can deeply mine the functionality and interactivity between design elements, thereby providing a more accurate semantic basis for personalized recommendation. By introducing a domain knowledge graph and integrating professional terms and concept relationships into the semantic network, the accuracy and practicality of the model can be improved, not only enriching the background knowledge of the semantic network but also better adapting to the design requirements of specific domains. Based on network embedding technology and deep learning algorithms, low-dimensional vector representation and optimization of the semantic network are carried out, and at the same time, the model is dynamically adjusted through preset evaluation metrics (such as accuracy and recall rate), which can ensure the continuous optimization of the semantic network. By constructing a semantic network model, the design team can quickly identify potential connections between design elements, accelerate the design innovation process, and improve design efficiency. The semantic entanglement effect generated by the fusion of word vector similarity and knowledge graph can significantly improve the depth, accuracy, and flexibility of semantic understanding of the system when processing natural language tasks. For example, when analyzing the "silk" material, the system automatically generates a dynamic light and shadow scheme for silk texture through the proximity relationship in the vector space (distance 0.32 from "fluid" and distance 0.29 from "light and shadow"). This innovative scheme is applied to the automotive interior design, resulting in a 19% increase in passenger experience satisfaction, verifying the cross-modal innovation ability driven by the algorithm.

[0020] In one embodiment of the present invention, the S213 includes: Define the semantic relationship between elements as the edges of the network; based on the analysis results of natural language processing technology, identify different types of semantic relationships such as similarity, correlation, and functional interaction between elements, and assign weights or type labels to each relationship; Evaluate the applicability of different network topologies; consider various structures such as scale-free networks, small-world networks, and random networks, analyze their respective characteristics and advantages, as well as their application potential in the semantic network of design elements; select the most suitable network topology according to the actual relationship characteristics between design elements; Based on the selected network topology and the defined nodes and edges, construct a preliminary semantic network model; use graph theory tools or software platforms to visualize the network and check the connectivity and integrity of the network.

[0021] By comparing the analysis results of natural language processing technology with the actual relationships in the network, check whether there are any incorrect or missing connections and make necessary corrections; Apply community detection algorithms to identify the community structure in the network; a community refers to a group of tightly connected nodes in the network, which may represent a group of design elements with common characteristics or functions; by identifying the community structure, further obtain the internal associations and hierarchical structures between elements; Adjust the network structure based on the community detection results; for example, merge highly overlapping communities, split overly large communities, or enhance the connections between communities, etc., and construct a dynamic semantic network through time series data.

[0022] Deeply explore and analyze the above technical solutions to find unexpected technical effects.

[0023] The working principle and effects of the above technical solutions are as follows: By defining the semantic relationships between elements and assigning weights or type labels, combined with the evaluation of various network topologies, a semantic network model of design elements can be accurately constructed, and the complex relationships between design elements can be revealed, which can help designers better understand and optimize each link in the design process, improve design quality, efficiency, and innovation. At the same time, it can also provide effective support for multidisciplinary collaboration and cross-domain design; Based on the community detection algorithm, identify the community structure in the network, and adjust the network structure according to the community detection results, which can optimize the hierarchy and connectivity of the network; At the same time, constructing a dynamic semantic network through time series data can further improve the adaptability of the model to changes in the relationships of design elements; By identifying the community structure, the internal associations and hierarchical structures between design elements can be further obtained, thus providing deeper semantic support for design innovation; By combining the domain knowledge graph and the community detection algorithm, more professional information and background knowledge can be introduced to improve the accuracy and practicality of the semantic network; The community detection algorithm can identify groups of closely connected design elements, and the groups represent groups of design elements with common characteristics or functions, providing strong support for design optimization and personalized recommendation; By comparing the analysis results of natural language processing technology with the actual relationships in the network, checking and correcting incorrect or missing connections can ensure the integrity and connectivity of the semantic network, and further improve the dynamic optimization ability of the model.

[0024] In one embodiment of the present invention, the S214 includes: Based on the preliminary semantic network model, construct a dataset for network embedding training; the dataset should include design element nodes, semantic relationship edges between elements, and possible attribute information; and preprocess the dataset, including removing noise data, balancing data distribution, and enhancing data sparsity. Use the selected network embedding algorithm and the preprocessed dataset to train the network embedding model; the model should be able to learn the representation of design elements in the low-dimensional vector space; and monitor the training process, including the convergence of the loss function, the generalization ability of the model, etc. Evaluate the accuracy of the network embedding results, and use indicators such as semantic similarity measurement and clustering effect evaluation to verify whether the embedding vectors can accurately reflect the positions and roles of design elements in the semantic network. Optimize the network embedding model according to the evaluation results; including adjusting model parameters, improving training strategies, introducing additional information sources, etc.

[0025] Apply the learned embedding vectors to scenarios such as similarity calculation, clustering analysis, and recommendation systems of design elements to verify their effectiveness in practical applications; conduct interpretive analysis on the embedding vectors. Through methods such as visualization techniques and feature importance evaluation, reveal the semantic relationships and information among design elements contained in the embedding vectors.

[0026] Iteratively optimize the network embedding model according to the feedback in practical applications and new design element data; may include updating the training dataset, adjusting the model structure, etc.

[0027] The working principle and effects of the above technical solutions are as follows: By constructing a high-quality network embedding dataset and using advanced embedding algorithms, design elements can be accurately mapped into a low-dimensional vector space, which helps to optimize the design process and support intelligent decision-making; at the same time, the embedding vectors can accurately reflect the positions and roles of design elements in the semantic network, providing an efficient and compact semantic representation for subsequent applications; during the training process, by monitoring the convergence of the loss function and the generalization ability of the model, combined with data preprocessing (such as removing noise and balancing data distribution) and model parameter optimization, the stability and adaptability of the network embedding model can be significantly improved; through the use of visualization techniques and feature importance evaluation methods to conduct interpretive analysis on the embedding vectors, the semantic relationships and hierarchical structures among design elements can be clearly revealed, providing an intuitive basis for design decisions; through similarity calculation and clustering analysis using embedding vectors, the similarities and group characteristics among design elements can be accurately identified, providing strong support for personalized recommendation and design optimization; based on the feedback from practical applications and new data, iteratively optimizing the model can ensure that the network embedding model can dynamically adapt to new design requirements and semantic changes, improving the long-term usability of the model; the learned embedding vectors are widely applied to scenarios such as similarity calculation, clustering analysis, and recommendation systems of design elements, verifying their efficiency and versatility in practical applications.

[0028] In an embodiment of the present invention, the S3 includes: S31. Generate a fusion plan based on a cross-domain fusion algorithm, combining a cultural semantic network, user preference prediction, and technical feasibility analysis; S32. Use VR (Virtual Reality) and AR (Augmented Reality) technologies to create an interactive creative workshop; collect instant feedback from target users on product design through an online platform, and use machine learning algorithms to adjust the design direction in real time; based on a multi-dimensional performance evaluation model, including creativity, cultural value, market potential, and technical implementation difficulty, continuously iteratively optimize the design. S33. Generate the documents required for production according to the final design plan.

[0029] The working principle and effects of the above technical solution are as follows: Based on the cross-domain fusion algorithm, combined with the cultural semantic network, user preference prediction, and technical feasibility analysis, it can generate unprecedented creative combinations, break through the limitations of traditional design thinking, and provide a new perspective for product design; create an interactive creative workshop with VR and AR technologies, combine the instant feedback of the online platform and the real-time adjustment of the machine learning algorithm to adjust the design direction, which can improve the design efficiency and user participation; based on the multi-dimensional performance evaluation model (including creativity, cultural value, market potential, and technical implementation difficulty), continuously iterate and optimize the design to ensure that the design plan reaches the optimal level in multiple key indicators; directly generate the documents required for production according to the final design plan, simplify the transition process from design to production, reduce human errors, and improve production efficiency; ensure that the design plan can accurately meet the market demand and enhance the market competitiveness of the product by collecting user feedback in real time and dynamically adjusting the design direction; combine the machine learning algorithm and the multi-dimensional evaluation model to provide data support for design decisions and reduce the risks brought by subjective judgments.

[0030] In one embodiment of the present invention, the S31 includes: S311. Optimize the parameters and test the performance of the cross-domain fusion algorithm; combine the cultural semantic network and the user preference prediction results, and generate innovative design plans through the fusion algorithm; evaluate the generated design plans based on the multi-dimensional performance evaluation model, and perform iterative optimization according to the evaluation results; build an interactive creative workshop based on VR / AR technologies and platforms, and users can freely combine and customize design elements through design tools and material libraries; S312. Optimize the user experience and functions of the workshop according to user feedback and test results; establish a multi-dimensional evaluation index system including creativity, practicality, cultural fit, etc.; score and rank the creative plans through an automatic evaluation system based on the machine learning algorithm; screen out excellent creative plans in combination with the automatic evaluation results; display and promote the screened creative plans through an online platform.

[0031] The working principle and effects of the above technical solution are as follows: Through cross-domain fusion algorithms, combined with cultural semantic networks and user preference prediction, it is possible to break through domain limitations, generate innovative design solutions, and obtain more creative combinations; an automatic evaluation system based on a multi-dimensional performance evaluation model (such as creativity, practicality, cultural fit, etc.) and machine learning algorithms can accurately score and rank creative solutions, screen out excellent solutions and perform iterative optimization; use VR / AR technology to build an interactive creative workshop where users can freely combine and customize design elements through design tools and material libraries, enhancing user experience and participation; display and promote the selected excellent creative solutions through an online platform, combined with a multi-dimensional evaluation index system, which can quickly transform creativity into practical applications while increasing the market exposure of the solutions; according to user feedback and test results, continuously optimize the user experience and functions of the workshop to ensure that the design solutions can dynamically adapt to market demands and enhance market competitiveness; the automatic evaluation system combined with a multi-dimensional performance evaluation model can quickly identify excellent creative solutions, reducing the time cost of manual screening and providing a scientific basis for design decisions; the application of cross-domain fusion technology not only promotes innovation in the design field but also provides support for the digital transformation and upgrading of traditional industries by integrating knowledge and technologies from different fields, promoting social progress.

[0032] In one embodiment of the present invention, the S32 includes: S321. Real-time collect feedback data of users on design works, such as comments, likes, and shares; apply sentiment analysis algorithms to judge the sentiment tendency of user comments and construct a sentiment dictionary; S322. Use natural language processing technology to extract keywords and themes in user comments to understand users' concerns and needs; apply the feedback results to design optimization and market strategy adjustment; combined with the characteristics of cultural and creative design, construct a multi-dimensional performance evaluation model including creativity, cultural value, market potential, technical implementation difficulty, etc.; quantify each index in the evaluation model to form comparable numerical indexes; S323. Based on the automatic evaluation system, conduct multi-dimensional performance evaluation on design works; optimize and iterate the design works according to the evaluation results, and continuously optimize the evaluation model and improve the evaluation accuracy.

[0033] The working principle and effects of the above technical solution are as follows: By collecting user feedback data in real time and combining sentiment analysis algorithms and natural language processing technologies, it is possible to accurately judge the user's sentiment tendency and extract key information, helping the design team quickly understand the true needs and concerns of users; applying the user feedback results to design optimization and market strategy adjustment, and constructing a multi-dimensional performance evaluation model in combination with the characteristics of cultural and creative design, it is possible to quantitatively evaluate design works from multiple aspects such as creativity, cultural value, market potential, and technical implementation difficulty, providing a scientific basis for design optimization; based on the automatic evaluation system, conducting multi-dimensional performance evaluation on design works and optimizing and iterating according to the evaluation results, it is possible to continuously improve the market adaptability and competitiveness of design works; by quantitatively processing evaluation indicators, forming comparable numerical indicators, and dynamically adjusting the evaluation model in combination with user feedback, it is ensured that design decisions are more scientific and flexible, and can adapt to market changes in a timely manner; through the above technical solutions, not only the creativity and cultural value of design works are improved, but also the feasibility of design solutions is ensured through the evaluation of technical implementation difficulty.

[0034] In one embodiment of the present invention, the S321 includes: Automatically collect various feedback data of users on design works, including but not limited to comments, likes, shares, browsing duration, etc.; preprocess the collected data, including removing duplicates, cleaning noise data, standardizing formats, etc.; Based on sentiment analysis algorithms, judge the sentiment tendency of user comments, distinguishing positive, negative, and neutral comments; construct a sentiment dictionary based on user comments, which should not only contain common sentiment words, but also cover sentiment expressions specific to the cultural and creative design field; Use the sentiment dictionary to quantify the sentiment of comments, assign a sentiment score to each comment, so as to more intuitively understand the distribution of users' sentiment tendencies towards design works; Use natural language processing technology to extract keywords from user comments, and identify the focus and hot issues that users are concerned about; Based on the keywords, conduct topic recognition, and classify similar comments under the same topic; the topic recognition algorithm should be able to recognize multi-level topic structures, reflecting the diversity and hierarchy of user needs.

[0035] Conduct in-depth analysis on the identified topics, including the subdivision of user preferences, the preference analysis of design elements, the feedback on market strategies, etc.; Integrate the results of sentiment analysis, keyword extraction, topic recognition, etc. to form a comprehensive user feedback report; apply the user feedback report to design optimization and market strategy adjustment; improve the design work according to the preferences and needs of users; at the same time, adjust the market strategy to better meet user needs.

[0036] The working principle and effects of the above technical solution are as follows: By automatically collecting multi-dimensional user feedback data (including comments, likes, shares, browsing duration, etc.) and performing in-depth preprocessing and sentiment analysis, it is possible to comprehensively and accurately capture the true emotions and needs of users for design works; Through sentiment quantification, keyword extraction, and multi-level theme recognition, not only can the user sentiment tendency be distinguished, but also the user preferences can be segmented, and the feedback on design elements and marketing strategies can be analyzed in depth to reveal the diversity and hierarchy of user needs; Integrate the results of sentiment analysis, keyword extraction, and theme recognition into a comprehensive user feedback report and directly apply it to design optimization and marketing strategy adjustment to ensure that design improvements and marketing decisions are based on real user data, enhancing scientificity and effectiveness; Making targeted improvements to design works based on user feedback can quickly respond to market changes, improve the user experience and market adaptability of design works, and enhance their competitiveness in the cultural and creative field; Construct a specific sentiment dictionary covering the cultural and creative design field to ensure the accuracy of sentiment analysis, and at the same time inject richer emotions and cultural connotations into design works to enhance the attractiveness and cultural value of cultural and creative products; By continuously monitoring user feedback and dynamically adjusting design and marketing strategies, a closed-loop optimization mechanism is formed to ensure that design works and marketing strategies can continuously adapt to user needs and market changes.

[0037] In one embodiment of the present invention, the S33 includes: S331. According to the design scheme, use CAD software to automatically generate high-precision drawings, including two-dimensional drawings and three-dimensional models; Combine 3D printing technology to convert the design work into a physical model for preview and testing; S332. Review the generated CAD drawings and 3D printed models and make optimization adjustments as needed.

[0038] The working principle and effects of the above technical solution are as follows: Using CAD software to automatically generate high-precision 2D drawings and 3D models, and combining 3D printing technology to quickly transform the design into a physical model, which shortens the time from design to physical verification and improves design efficiency; reviewing and optimizing the generated CAD drawings and 3D printing models to ensure that the design works meet high-quality standards in terms of accuracy, function, and appearance, reducing errors and rework in production; through the preview and testing of the physical model, design defects or functional problems can be intuitively discovered before production, and adjusted and optimized in a timely manner, reducing production costs and risks; the high-precision CAD drawings and physical models provide an intuitive communication tool for the design team, customers, and production departments, reducing design mistakes caused by differences in understanding and improving collaboration efficiency; quickly generating a physical model and making optimization adjustments can accelerate the product iteration cycle, enabling the design solution to respond to market demands faster and enhancing the market competitiveness of the product; combining CAD technology with 3D printing can provide strong technical support for design innovation, promote the seamless transformation of design from concept to entity, and facilitate the deep integration of design and manufacturing.

[0039] An embodiment of the present invention, a cultural and creative design assistance system based on element fusion, includes a memory, a processor, and a computer program stored on the memory and executable on the memory. The processor executes the program to implement the cultural and creative design assistance method based on element fusion as described in any one of the above.

[0040] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A cultural and creative design assistance method based on element fusion, characterized in that The method includes: S1. Obtain design elements and classify them; S2. Based on the deep learning algorithm, construct a semantic network among the elements, convert the semantic network into a low-dimensional vector space through network embedding technology, and combine social media data to analyze user preferences, sentiment tendencies, and future trends; S3. Generate a fusion plan and continuously iterate and optimize the design.

2. The cultural and creative design auxiliary method based on element fusion according to claim 1 is characterized in that: The S1 includes: S11. Obtain cultural heritage materials, extract design elements, and analyze the cultural heritage materials; S12. Classify and organize the extracted design elements; integrate them to form a cross-domain modern art and technology element library; S13. Judge the sentiment tendency of the content posted by users; monitor the design hotspots on social media in real time, and analyze the reasons and trends behind the hotspots; S14. Construct a user profile, use the deep learning algorithm to extract features of the design elements; based on the extracted features, conduct intelligent classification; according to the classification results, design a label system; S15. Construct an association map among the design elements to reveal the internal connections between the elements.

3. The cultural and creative design auxiliary method based on element fusion according to claim 1 is characterized in that: The S2 includes: S21. Analyze the semantic relationships among the design elements, and construct a semantic network model among the design elements through complex network theory; S22. Combine time series analysis and machine learning algorithms to predict the development trends of the design elements, and display the semantic network in a graphical way based on a visualization tool; S23. Collect users' design preferences and behavior data through multiple methods; based on the collected data, apply machine learning algorithms to construct a user preference model; S24. Monitor the sentiment tendency of users towards design works in real time, obtain the changes in users' preferences and feedback; according to the user preference model and the results of sentiment tendency monitoring, provide personalized design element recommendations for users; S25. Monitor the latest developments in the international design community in real time, analyze the evolution laws of global design trends; combine user preference analysis and market research data to predict the changes in the future market demand for design elements; S26. Based on trend analysis and market demand prediction, formulate targeted innovative design strategies; apply the innovative strategies to actual designs, and evaluate and optimize them through user feedback and market performance.

4. The method for assisting cultural and creative design based on element fusion according to claim 3, wherein The S21 includes: [[ID=I8]]SIlI. Use natural language processing technology to preliminarily analyze the similarity and correlation among the design elements; based on the preliminary analysis results, preliminarily construct the semantic connections among the elements; S212. Understand the functionality and interactivity among the elements by analyzing the semantic roles of the elements in sentences; S213. Based on complex network theory, regard the design elements as nodes and the semantic relationships among the elements as edges to construct a preliminary semantic network model; S214. Based on network embedding technology, embed the semantic network into a low-dimensional vector space; through training the network embedding model, obtain the vector representation of each element; S215. Use the deep learning algorithm to further learn and optimize the semantic network; combine the domain knowledge graph to refine and improve the semantic network; S216. Evaluate the accuracy and reliability of the semantic network model based on preset evaluation metrics; optimize and adjust the semantic network model according to the evaluation results.

5. The method for assisting cultural and creative design based on element fusion according to claim 4, wherein The S213 includes: Define the semantic relationships between elements as the edges of the network; based on the analysis results of natural language processing technology, identify different types of semantic relationships between elements, and assign weights or type labels to each relationship; Evaluate the applicability of different network topologies; select the most suitable network topology according to the actual relationship characteristics between design elements; Construct a preliminary semantic network model based on the selected network topology and the defined nodes and edges; use graph theory tools or software platforms to visualize the network and check the connectivity and integrity of the network; Check for any incorrect or missing connections by comparing the analysis results of natural language processing technology with the actual relationships in the network, and make corrections; Apply community detection algorithms to identify the community structure in the network; further obtain the internal associations and hierarchical structures between elements by identifying the community structure; Adjust the network structure based on the community detection results; and construct a dynamic semantic network using time series data.

6. The method for assisting cultural and creative design based on element fusion according to claim 1, wherein The S3 includes: S31. Generate a fusion plan based on cross-domain fusion algorithms; S32. Continuously iterate and optimize the design; S33. Generate the files required for production according to the final design plan.

7. The method for assisting cultural and creative design based on element fusion according to claim 6, characterized in that, The S31 includes: S311. Generate innovative design plans through fusion algorithms; evaluate the generated design plans and perform iterative optimization according to the evaluation results; build an interactive workshop based on VR / AR technology and platforms; S312. Optimize the workshop according to user feedback and test results; establish a multi-dimensional evaluation index system to score and rank creative plans; combine the automatic evaluation results to screen out creative plans; and display and promote them.

8. The method for assisting cultural and creative design based on element fusion according to claim 6, wherein The S32 includes: S321. Judge the sentiment tendency of user comments and construct a sentiment dictionary; S322. Extract keywords and themes from user comments; construct a multi-dimensional performance evaluation model for quantitative processing; S323. Conduct multi-dimensional performance evaluations on design works; optimize and iterate the design works according to the evaluation results.

9. The method for assisting cultural and creative design based on element fusion according to claim 6, wherein The S33 includes: S331. Automatically generate high-precision drawings using CAD software according to the design plan, and convert the design work into a physical model for preview and testing; S332. Review the generated CAD drawings and 3D printing models, and optimize and adjust them as needed.

10. A cultural and creative design assistance system based on element fusion, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the memory. The processor executes the program to implement the cultural and creative design assistance method based on element fusion as described in any one of claims 1-9.

Images