Intelligent creative method and system based on design elements

Abstract

The invention relates to the technical field of creative design, in particular to an intelligent creative method and system based on design elements, and the method comprises the following steps: collecting design element data, analyzing dependency and influence among elements through a graph network, extracting element attributes, calibrating dependency intensity, and carrying out element association mapping to obtain a design element relation graph. According to the method, analysis dimensions of design data are enhanced through deep utilization of a graph network, deep insight of complex relations among design elements is provided, element dependence and influence are evaluated in a quantitative mode, data driving performance of a decision process is ensured, and sentiment analysis is carried out in combination with a design element relation graph. The design scheme can reflect user emotion requirements in detail, design template updating dynamically adapting to market changes, design iteration acceleration and reaction speed and market competitiveness improvement are achieved, the effectiveness of the scheme is ensured through design evaluation and analogue simulation of user experience, and the market release risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of creative design technology, and in particular to an intelligent creative method and system based on design elements. Background Art

[0002] The field of creative design technology mainly involves the use of technical means to enhance, optimize and automate the design process. This field integrates multiple disciplines such as artificial intelligence, computer graphics, user interface design and interaction technology to solve challenges in traditional design in an innovative way. In this field, AI technology, especially machine learning and neural networks, is used to analyze design elements and user preferences to automatically generate or propose innovative design solutions. It can process large amounts of data, identify design trends, and predict user needs, thereby helping designers to quickly iterate and optimize creative output.

[0003] Among them, the intelligent creative method of design elements focuses on using intelligent tools and algorithms to create or improve design elements. The main purpose is to reduce manual labor in the design process through automated tools and improve design quality and innovation. Using this method, designers can access the intelligent recommendation system in the initial creative stage, which can provide design solutions that meet current market trends and user preferences. In addition, it can also identify potential design problems in the early stages of product development, thereby reducing the cost and time of later modifications. It is widely used in many design fields such as industrial design, fashion design, and interface design.

[0004] In actual operation, existing technologies usually lack the ability to fully analyze and update the relationship between design elements in real time, which makes it difficult to accurately match user emotions and cultural needs during the design process, limiting the market sensitivity of design solutions. In addition, traditional technologies perform poorly in the rapid integration of user feedback and market changes, often resulting in long design cycles and inefficient iterations. The lack of an effective dynamic adjustment mechanism for design elements makes it difficult for design teams to adjust solutions in a timely manner when faced with rapid market changes, increasing costs and time consumption. User experience verification is usually not timely or accurate enough, increasing the possibility of design failure in the market. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent creative method and system based on design elements.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an intelligent creative method based on design elements, comprising the following steps:

[0007] S1: Collect design element data, analyze the dependencies and influences between elements through graph networks, extract element attributes, calibrate dependency strength, perform element association mapping, and obtain a design element relationship diagram;

[0008] S2: Based on the design element relationship diagram, sentiment analysis is performed to analyze the emotional response of users to design elements under differentiated cultural backgrounds, and user evaluation data is aggregated based on the analysis results to divide the sentiment categories and obtain cultural preference clustering results;

[0009] S3: Based on the cultural preference clustering results and combined with user feedback data, the design elements are adjusted to match the different cultural characteristics, the user interaction data is analyzed according to the adjustment results, historical design success cases are compared, the element configuration is dynamically adjusted, the design template is updated, and a dynamic adaptive design solution is generated;

[0010] S4: Apply the dynamic adaptive design solution to conduct design evaluation, verify the design through simulation of user experience, determine the design adaptability and user satisfaction, and obtain the final intelligent creative solution for the design elements.

[0011] As a further solution of the present invention, the step of obtaining the design element relationship diagram is:

[0012] S111: Collect design elements and use formulas.

[0013] E={e1,e2,…,e i}

[0014] Get the initial design element set E, where e i It is a single design element;

[0015] S112: Based on the initial design element set, using the formula:

[0016]

[0017] Calculate the dependency strength A between elements ij , representing the element e i and e j The dependency strength between them is output as a dependency matrix, where α A , β A and γ A It is an adjustment parameter used to ensure flexibility and accuracy of calculation;

[0018] S113: Analyze based on the dependency matrix, using the formula:

[0019]

[0020] Calculate the impact score S for each design element i , output the design element influence assessment results, where n represents the number of design elements;

[0021] S114: Combining the design element influence assessment result and the element attribute, using the formula:

[0022]

[0023] Calculation element e i and e j The correlation strength G ij , a design element relationship diagram is generated, where w1 and w2 are the parameters for adjusting the influence of the dependency strength and influence difference, respectively, and w3 is the adjustment parameter for the influence of the element attribute difference.

[0024] As a further solution of the present invention, the steps of analyzing the emotional response of users to design elements under the differentiated cultural background are:

[0025] S211: Based on the design element relationship diagram, combined with user comment data, emotional vocabulary is mapped, and formula is used.

[0026]

[0027] Calculate the association strength F between element i and sentiment word j ij , output the sentiment vocabulary mapping result, where G ik is the weight of the relationship between element i and element k, r kj is the association frequency of element k with sentiment word j in user comments, a is the adjustment index used to enhance or weaken the influence of frequency, λ is the smoothing parameter used to adjust the influence of distance attenuation, and d kj is the distance attenuation factor between elements, and n represents the number of design elements;

[0028] S212: According to the sentiment vocabulary mapping result, the formula is adopted:

[0029]

[0030] Calculate the sentiment preference score C of the kth cultural background k , generate sentiment preference analysis results, where b is the exponential transformation of sentiment intensity, c i is the cultural weight factor, h ik is a reconciliation factor used to balance the impact of different cultures. ik is the sentiment mapping score under the kth cultural background, and m is the type of different cultural backgrounds;

[0031] S213: Using the sentiment preference analysis results, integrating them, using the formula:

[0032]

[0033] Calculate the weighted sentiment preference index P and output the sentiment preference overview, where v k is the comprehensive importance of the k-th cultural background, which is used to provide a weighted consideration of different cultural backgrounds.

[0034] As a further solution of the present invention, the steps of obtaining the cultural preference clustering results are:

[0035] S221: According to the emotional preference overview, aggregate user evaluations, using the formula:

[0036]

[0037] Calculate the aggregated user evaluation index D and obtain the aggregated evaluation result, where u i is the weight of the i-th user, which is used to adjust the influence of user evaluation, P i is the sentiment preference index of the i-th user, ln(P i +1) is used to smooth extreme values, and p represents the number of users;

[0038] S222: Based on the aggregated evaluation results, sentiment categories are divided using the formula:

[0039]

[0040] Calculate the normalized sentiment category score Z to obtain the sentiment category division result, where max(D) represents the maximum value of the aggregated user evaluation index;

[0041] S223: Based on the emotion classification result, the formula is used:

[0042]

[0043] Calculate the comprehensive cultural preference index H and obtain the cultural preference clustering result, where μ k is the influence coefficient of the kth culture, which is used to adjust the contribution of different cultures to the clustering results, and m represents the types of different cultural backgrounds.

[0044] As a further solution of the present invention, the adjustment steps of the design elements are:

[0045] S311: Analyze the cultural preference clustering results, using the formula,

[0046]

[0047] Calculate the comprehensive preference weight W of the i-th culture i , we get the comprehensive analysis results of cultural preferences, where h k is the cluster weight of preference k in the ith cultural background, p kis the influence coefficient of preference k, N represents the cultural preference type;

[0048] S312: Based on the comprehensive analysis results of the cultural preferences and combined with user feedback, the design elements are adjusted and the formula is adopted.

[0049]

[0050] Calculate the adjusted design element value Y′, where Y is the original design element set and λ Y is an adjustment factor used to enhance the impact of user feedback, f j is the data about element j in user feedback, W j is the comprehensive preference weight of the jth culture, and m represents the types of different cultural backgrounds;

[0051] S313: According to the adjusted design element value, the design element adjustment content and the expected effect are integrated and recorded to obtain the adjusted design element result.

[0052] As a further solution of the present invention, the steps of obtaining the dynamic adaptive design solution are:

[0053] S321: Analyze user interaction data according to the adjusted design element results, and use the formula:

[0054]

[0055] Calculate the user interaction index I to evaluate the effectiveness of the design, where L i is the interactive data indicator, e′ i is the adjusted design element, l is the number of adjusted design elements;

[0056] S322: Use the user interaction index to update the design template, using the formula:

[0057] T = τ T Q+μ T I

[0058] Calculate the comprehensive score T of the updated design template and output the optimized design template, where τ T and μ T is the adjustment coefficient, Q is the template configuration score obtained from the comparison of historical cases;

[0059] S323: Based on the optimized design template, combined with market and user data, matching market changing needs, and generating a dynamic adaptive design solution.

[0060] As a further solution of the present invention, the steps for obtaining the final intelligent creative solution of the design element are:

[0061] S411: Apply the dynamic adaptive design scheme, using the formula,

[0062]

[0063] Calculate the evaluation score K and get the preliminary evaluation result, where X i is the i-th element in the design, α i is the weight factor that adjusts the impact of each design element, d i is the nonlinear coefficient used to adjust the influence of the element, and n represents the number of design elements;

[0064] S412: Based on the preliminary evaluation results, simulation is performed to analyze the user experience, using a formula,

[0065]

[0066] Calculate the user experience score U and get the simulation results, where κ j is the weight coefficient of each element in the simulation, which is used to adjust the impact of user experience, r j is a nonlinear adjustment coefficient used to simulate complex user interaction effects, and M is the total number of user ratings;

[0067] S413: combining the simulation results and the preliminary evaluation results, balancing the evaluation scores and the user experience scores, optimizing the overall effect and market adaptability of the design solution, and outputting the final intelligent creative solution of the design elements.

[0068] An intelligent creative system based on design elements, including:

[0069] The element analysis module collects design elements, analyzes the dependency strength between elements, scores the influence of each design element, combines it with element attributes, calculates the correlation strength between elements, and generates a design element relationship diagram;

[0070] The sentiment mapping module maps sentiment vocabulary based on the design element relationship diagram and combines user comment data, calculates the sentiment preference score of the cultural background, and integrates and outputs a sentiment preference overview;

[0071] The sentiment clustering module aggregates user comments according to the sentiment preference overview, divides the sentiment categories and calculates the normalized sentiment category scores, analyzes the comprehensive cultural preference indicators, and obtains the cultural preference clustering results;

[0072] The preference adjustment module analyzes the cultural preference clustering results, calculates the comprehensive preference weight of the culture, adjusts the design elements in combination with user feedback, integrates and records the design element adjustment content and expected effects, and obtains the adjusted design element results;

[0073] The template update module analyzes user interaction data and calculates user interaction indicators according to the adjusted design element results, uses the user interaction indicators to update the design template, combines market and user data, matches market change needs, and generates a dynamic adaptive design solution;

[0074] The design optimization module applies the dynamic adaptive design solution, calculates the evaluation score, performs simulation, analyzes the user experience, balances the evaluation score and the user experience score, optimizes the design solution, and outputs the final intelligent creative solution of the design elements.

[0075] Compared with the prior art, the advantages and positive effects of the present invention are:

[0076] In the present invention, the analytical dimension of design data is enhanced through the in-depth use of graph networks, providing deep insights into the complex relationships between design elements, using quantitative methods to evaluate element dependencies and influences, ensuring the data-driven nature of the decision-making process, and combining sentiment analysis with design element relationship graphs to enable design solutions to meticulously reflect user emotional needs, enhance product personalization and market appeal, enhance the cultural adaptability of design through precise clustering of cultural preferences and instant integration of user feedback, dynamically adapt to market changes in design templates to update, accelerate design iterations, improve response speed and market competitiveness, and simulate design evaluation and user experience to ensure the effectiveness of the solution and reduce market launch risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a schematic diagram of the steps of the present invention;

[0078] Figure 2 A flowchart for obtaining a design element relationship diagram of the present invention;

[0079] Figure 3 The flowchart of analyzing the emotional response of users to design elements under the differentiated cultural background of the present invention;

[0080] Figure 4 A flowchart for obtaining the cultural preference clustering results of the present invention;

[0081] Figure 5 A flow chart for adjusting the design elements of the present invention;

[0082] Figure 6 A flowchart for obtaining the dynamic adaptive design scheme of the present invention;

[0083] Figure 7 The present invention is a flowchart for obtaining the final intelligent creative solution for the design elements. DETAILED DESCRIPTION

[0084] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0085] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0086] See also Figure 1 , an intelligent creative approach based on design elements, includes the following steps:

[0087] S1: Collect design element data, analyze the dependencies and influences between elements through graph networks, extract element attributes, calibrate dependency strength, perform element association mapping, and obtain a design element relationship diagram;

[0088] S2: Based on the design element relationship diagram, sentiment analysis is performed to analyze the emotional response of users to design elements under differentiated cultural backgrounds. Based on the analysis results, user evaluation data is aggregated, sentiment categories are divided, and cultural preference clustering results are obtained;

[0089] S3: Based on the cultural preference clustering results and combined with user feedback data, the design elements are adjusted to match the different cultural characteristics. According to the adjustment results, the user interaction data is analyzed, and historical design success cases are compared. The element configuration is dynamically adjusted, the design template is updated, and a dynamic adaptive design solution is generated.

[0090] S4: Apply dynamic adaptive design solutions to conduct design evaluation, verify the design through simulation of user experience, determine the design adaptability and user satisfaction, and obtain the final intelligent creative solution for the design elements.

[0091] The design element relationship diagram includes the element dependency diagram, influence matrix and attribute mapping table. The cultural preference clustering results include emotional response analysis records, evaluation aggregation data and differentiated cultural indicators. The dynamic adaptive design plan includes cultural adjustment strategies, template update records and configuration adjustment logs. The final intelligent creative plan of design elements includes adaptability verification data, satisfaction feedback analysis records and user experience simulation reports.

[0092] See also Figure 2 , the steps to obtain the design element relationship diagram are:

[0093] S111: Collect design elements and use formulas.

[0094] E={e1,e2,…,e i}

[0095] Get the initial design element set E, where e i It is a single design element;

[0096] S112: Based on the initial set of design elements, using the formula,

[0097]

[0098] Calculate the dependency strength A between elements ij , representing the element e i and e j The dependency strength between them is output as a dependency matrix, where α A , β A and γ A It is an adjustment parameter used to ensure flexibility and accuracy of calculation;

[0099] S113: Based on the dependency matrix, the formula is used.

[0100]

[0101] Calculate the impact score S for each design element i , output the design element influence assessment results, where n represents the number of design elements;

[0102] S114: Combine the design element impact assessment results and element attributes, using the formula,

[0103]

[0104] Calculation element e i and e j The correlation strength G ij , a design element relationship diagram is generated, where w1 and w2 are the parameters for adjusting the influence of the dependency strength and influence difference, respectively, and w3 is the adjustment parameter for the influence of the element attribute difference.

[0105] Assume e1=1, e2=2, and so on, then:

[0106] E={1,2,…,e i}

[0107] Assume α A =2,β A =1,γA =0.5, e i =3,e j =4 (obtained from the initial design element set).

[0108] Substituting into the formula, we get:

[0109]

[0110] A ij =12.63 represents the design element e i and e j The dependency strength between them, a higher value indicates that there is a strong mutual dependence between the two elements.

[0111] Assume there are 3 elements,

[0112] For element e1:

[0113]

[0114] The elements e2 and e3 can be calculated similarly.

[0115] S1=5.88 represents the influence score of e1, which indicates that the overall influence of element e1 in the design is relatively high.

[0116] Assume w1 = 1, w2 = 0.5, w3 = 0.1, e i =3,e j =4, S i =5.88, S j =4.5.

[0117] Substituting into the formula, we get:

[0118] |S i -S j |=|5.88-4.5|=1.38

[0119]

[0120] G ij =10.12 means in the design element relationship diagram, e i and e j The connection strength is 10.12. This value indicates that e i and e j The relationship between the two is quite strong throughout the design, reflecting the i and e j importance and interactions.

[0121] See also Figure 3, the analysis steps of users’ emotional responses to design elements in different cultural backgrounds are:

[0122] S211: Based on the design element relationship diagram, combined with user comment data, mapping sentiment vocabulary, using formula,

[0123]

[0124] Calculate the association strength F between element i and sentiment word j ij , output the sentiment vocabulary mapping result, where G ik is the weight of the relationship between element i and element k, r kj is the association frequency of element k with sentiment word j in user comments, a is the adjustment index used to enhance or weaken the influence of frequency, λ is the smoothing parameter used to adjust the influence of distance attenuation, and d kj is the distance attenuation factor between elements, and n represents the number of design elements;

[0125] S212: According to the sentiment vocabulary mapping results, the formula is used:

[0126]

[0127] Calculate the sentiment preference score C of the kth cultural background k , generate sentiment preference analysis results, where b is the exponential transformation of sentiment intensity, c i is the cultural weight factor, h ik is a reconciliation factor used to balance the impact of different cultures. ik is the sentiment mapping score under the kth cultural background, and m is the type of different cultural backgrounds;

[0128] S213: Use the sentiment preference analysis results to integrate and use the formula,

[0129]

[0130] Calculate the weighted sentiment preference index P and output the sentiment preference overview, where v k is the comprehensive importance of the k-th cultural background, which is used to provide a weighted consideration of different cultural backgrounds.

[0131] Suppose there are three design elements mapped to a sentiment word:

[0132] G ik =[0.8, 0.6, 0.9], r kj =[3,2,5],a=2,λ=0.5,d kj =[1, 2, 1].

[0133] Substitute into the formula and calculate:

[0134] F ij =0.8×3 2 / (1+0.5×1)+0.6×2 2 / (1+0.5×2)+0.9×5 2 / (1+0.5×1)

[0135] F ij =0.8×9 / 1.5+0.6×4 / 2+0.9×25 / 1.5

[0136] F ij =4.8+1.2+15=21

[0137] Calculation result F ij =21 means that the comprehensive correlation strength of element i to sentiment word j among all design elements is 21. This value reflects the significance and relevance of sentiment words among elements.

[0138] Assume that there are three cultural backgrounds that influence a sentiment word:

[0139] F ik =[21, 15, 18] (obtained from the above calculation), c i =[0.5, 0.3, 0.2], b = 1.5, h ik =[1, 1, 1], cultural reconciliation factor, simplified to 1.

[0140] Substituting into the formula, we get:

[0141]

[0142] C k =48.1+17.43+15.28=80.81

[0143] Result C k =80.81 represents the weighted average of the overall sentiment preference score after considering different cultural weights. This value can be used to compare the sentiment differences in different cultural backgrounds and make corresponding design or marketing strategy adjustments.

[0144] Suppose there are three cultural background importance ratings:

[0145] v k =[0.4, 0.35, 0.25], C k =[80.81, 70, 90].

[0146] Substituting into the formula, we get:

[0147]

[0148] P≈0.4×8.99+0.35×8.37+0.25×9.49

[0149] P≈3.59+2.93+2.37=8.89

[0150] The result P=8.89 indicates that the weighted emotional preference index is the best under all cultural backgrounds. It can be used to guide product design and marketing strategies to ensure that they meet the emotional needs of consumers under different cultural backgrounds.

[0151] See also Figure 4 , the steps to obtain the cultural preference clustering results are:

[0152] S221: Based on the sentiment preference overview, aggregate user reviews using the formula,

[0153]

[0154] Calculate the aggregated user evaluation index D and obtain the aggregated evaluation result, where u i is the weight of the i-th user, which is used to adjust the influence of user evaluation, P i is the sentiment preference index of the i-th user, ln(P i +1) is used to smooth extreme values, and p represents the number of users;

[0155] S222: Based on the aggregated evaluation results, sentiment categories are divided using the formula:

[0156]

[0157] Calculate the normalized sentiment category score Z to obtain the sentiment category division result, where max(D) represents the maximum value of the aggregated user evaluation index;

[0158] S223: Based on the results of sentiment classification, the formula is used.

[0159]

[0160] Calculate the comprehensive cultural preference index H and obtain the cultural preference clustering result, where μ k is the influence coefficient of the kth culture, which is used to adjust the contribution of different cultures to the clustering results, and m represents the types of different cultural backgrounds.

[0161] Assume that there are three users with the following sentiment preference indexes:

[0162] P i =[2.5, 3.5, 4.5]

[0163] u i =[0.4, 0.3, 0.3]

[0164] The calculation process is as follows:

[0165] D=0.4×ln(2.5+1)+0.3×ln(3.5+1)+0.3×ln(4.5+1)

[0166] D=0.4×ln(3.5)+0.3×ln(4.5)+0.3×ln(5.5)

[0167] D≈0.4×1.2528+0.3×1.5041+0.3×1.7047

[0168] D≈0.5011+0.4512+0.5114=1.4637

[0169] The result D = 1.4637 represents the aggregated user evaluation index, which integrates the emotional preferences of all users and is smoothed by a logarithmic function. This value can be used for further emotional classification.

[0170] Assume that in a larger data set, max(D) = 2.0, then:

[0171]

[0172] The result Z = 0.7319 represents the normalized sentiment category score, providing a standardized measure that can be used to compare the sentiment preferences of different users.

[0173] Suppose there are three cultures, and their influence coefficients are:

[0174] μ k =[0.5, 0.3, 0.2]

[0175] Z k =[0.7319, 0.8, 0.6]

[0176] The calculation process is as follows:

[0177]

[0178] The result H = 0.242 represents the average value of the cultural preference clustering results, taking into account the influence coefficients of different cultures and providing a comprehensive cultural preference index that can be used for further market analysis and product positioning.

[0179] See also Figure 5 , the adjustment steps of the design elements are:

[0180] S311: Analyze the cultural preference clustering results, using the formula,

[0181]

[0182] Calculate the comprehensive preference weight W of the i-th culture i , we get the comprehensive analysis results of cultural preferences, where h k is the cluster weight of preference k in the ith cultural background, p k is the influence coefficient of preference k, N represents the cultural preference type;

[0183] S312: Based on the comprehensive analysis results of cultural preferences and combined with user feedback, adjust the design elements and use formulas.

[0184]

[0185] Calculate the adjusted design element value Y′, where Y is the original design element set and λ Y is an adjustment factor used to enhance the impact of user feedback, f j is the data about element j in user feedback, W j is the comprehensive preference weight of the jth culture, and m represents the types of different cultural backgrounds;

[0186] S313: According to the adjusted design element values, the design element adjustment contents and expected effects are integrated and recorded to obtain the adjusted design element results.

[0187] Assume there are three cultural preferences (N=3):

[0188] h k =[0.5, 0.3, 0.2]

[0189] p k =[1.2, 0.8, 1.0]

[0190] Substituting into the formula, we get:

[0191] W i =0.5×1.2+0.3×0.8+0.2×1.0

[0192] W i =0.6+0.24+0.2=1.04

[0193] The results show that for culture i, its comprehensive preference weight is 1.04. This value represents the weighted sum of different preference factors in this cultural background and is used for the adjustment of subsequent design elements.

[0194] Assume that the original design element Y = 10, and the adjustment coefficient λ Y =0.5, and consider feedback from two cultural backgrounds (m=2).

[0195] W j =[1.04, 0.95]

[0196] f j =[2,3]

[0197] Substituting into the formula, we get:

[0198] Y′=10+0.5×(1.04×2+0.95×3)

[0199] Y′=10+0.5×(2.08+2.85)

[0200] Y′=10+0.5×4.93=10+2.465=12.465

[0201] The adjusted design element value is 12.465. This value reflects the added value of the original design element after incorporating cultural preferences and user feedback, ensuring that the design is more adaptable.

[0202] See also Figure 6 , the steps to obtain the dynamic adaptive design solution are:

[0203] S321: Based on the adjusted design element results, analyze the user interaction data and use the formula,

[0204]

[0205] Calculate the user interaction index I to evaluate the effectiveness of the design, where L i is the interactive data indicator, e′ i is the adjusted design element, l is the number of adjusted design elements;

[0206] S322: Update the design template using the user interaction indicator, using the formula,

[0207] T = τ T Q+μ T I

[0208] Calculate the comprehensive score T of the updated design template and output the optimized design template, where τ T and μ T is the adjustment coefficient, Q is the template configuration score obtained from the comparison of historical cases;

[0209] S323: Based on the optimized design template, combined with market and user data, matching the changing market demands, a dynamic adaptive design solution is generated.

[0210] Assume there are three adjusted design elements (l=3), with corresponding user interaction data:

[0211] e′=[12.465, 14.230, 13.500]

[0212] Li =[1.2, 1.5, 1.3]

[0213] The calculation process is as follows:

[0214] I=1.2×12.465+1.5×14.230+1.3×13.500

[0215] I=14.958+21.345+17.55=53.853

[0216] It indicates that the user interaction index I = 53.853, which quantifies the intensity of users’ reactions to each adjusted design element and helps to understand which design elements attract the most attention and interaction from users.

[0217] Assume that the configuration score of historical successful cases is Q = 40, and the weight coefficient τ T =0.7 and μ T =0.3.

[0218] Substituting into the formula, we get:

[0219] T=0.7×40+0.3×53.853

[0220] T=28+17.6559=45.6559

[0221] The updated design template T = 45.6559. This value combines the historical design success experience and current user interaction data to ensure that the update of the design template can reflect the balance between historical success elements and actual user needs.

[0222] See also Figure 7 , the steps to obtain the final intelligent creative solution of design elements are:

[0223] S411: Apply a dynamic adaptive design solution, using formulas,

[0224]

[0225] Calculate the evaluation score K and get the preliminary evaluation result, where X i is the i-th element in the design, α i is the weight factor that adjusts the impact of each design element, d i is the nonlinear coefficient used to adjust the influence of the element, and n represents the number of design elements;

[0226] S412: Based on the preliminary evaluation results, conduct simulation, analyze user experience, and use formulas to

[0227]

[0228] Calculate the user experience score U and get the simulation results, where κ j is the weight coefficient of each element in the simulation, which is used to adjust the impact of user experience, r j is a nonlinear adjustment coefficient used to simulate complex user interaction effects, and M is the total number of user ratings;

[0229] S413: Combine the simulation results and preliminary evaluation results, balance the evaluation score and user experience score, optimize the overall effect and market adaptability of the design solution, and output the final intelligent creative solution of the design elements.

[0230] Assume there are two design elements:

[0231] X1=50,X2=30

[0232] α1=0.4,α2=0.6

[0233] d1=1.5,d2=1.2

[0234] Substituting into the formula, we get:

[0235] K=0.4×50 1.5 +0.6×30 1.2

[0236] K≈0.4×353.55+0.6×59.23

[0237] K≈141.42+35.538=176.958

[0238] The result K = 176.958 represents the adaptability score of the design solution, and a higher score indicates that the design solution is well adapted to the set requirements.

[0239] Combined with the above calculation results, assuming κ1=1.0, r1=1.0, then:

[0240] U=1.0×176.958 1.0 =176.958

[0241] The result U=176.958 represents the user experience score, which reflects the performance of the design in a simulated user environment.

[0242] An intelligent creative system based on design elements, including:

[0243] The element analysis module collects design elements, analyzes the dependency strength between elements, scores the influence of each design element, combines it with element attributes, calculates the correlation strength between elements, and generates a design element relationship diagram;

[0244] The sentiment mapping module maps sentiment vocabulary based on the design element relationship diagram, combines user comment data, calculates the sentiment preference score of the cultural background, and integrates and outputs a sentiment preference overview;

[0245] The sentiment clustering module aggregates user comments based on the sentiment preference overview, divides sentiment categories and calculates normalized sentiment category scores, analyzes comprehensive cultural preference indicators, and obtains cultural preference clustering results;

[0246] The preference adjustment module analyzes the cultural preference clustering results, calculates the comprehensive preference weight of the culture, adjusts the design elements based on user feedback, integrates and records the design element adjustment content and expected effects, and obtains the adjusted design element results;

[0247] The template update module analyzes user interaction data and calculates user interaction indicators based on the adjusted design element results. It uses the user interaction indicators to update the design template, combines market and user data, matches market changes, and generates a dynamic and adaptive design solution.

[0248] The design optimization module applies dynamic adaptive design solutions, calculates evaluation scores, and performs simulations to analyze user experience, balance evaluation scores and user experience scores, optimize design solutions, and output the final intelligent creative solution of design elements.

[0249] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent creative approach based on design elements, characterized by: The following steps are involved: Collect design element data, analyze the dependencies and influences between elements through graph networks, extract element attributes, calibrate dependency strength, perform element association mapping, and obtain a design element relationship diagram; According to the design element relationship diagram, sentiment analysis is performed to analyze the emotional response of users to design elements under differentiated cultural backgrounds, and user evaluation data is aggregated based on the analysis results to divide the sentiment categories and obtain cultural preference clustering results; Based on the cultural preference clustering results, combined with user feedback data, the design elements are adjusted to match the different cultural characteristics, the user interaction data is analyzed according to the adjustment results, historical design success cases are compared, the element configuration is dynamically adjusted, the design template is updated, and a dynamic adaptive design solution is generated; The dynamic adaptive design scheme is applied to conduct design evaluation, verify the design through simulation of user experience, determine the design adaptability and user satisfaction, and obtain the final intelligent creative scheme of the design elements.

2. The intelligent creative method based on design elements according to claim 1, characterized in that: The steps for obtaining the design element relationship diagram are: Collect design elements and use formulas. E={e1,e2,…,e i } Get the initial design element set E, where e i It is a single design element; Based on the initial set of design elements, the formula is adopted, Calculate the dependency strength A between elements ij , representing the element e i and e j The dependence strength between them is output as a dependency matrix, where α A , β A and γ A It is an adjustment parameter used to ensure flexibility and accuracy of calculation; Based on the dependency matrix, the formula is used: Calculate the impact score S for each design element i , output the design element influence assessment results, where n represents the number of design elements; Combining the design element influence assessment results with the element attributes, the formula is used: Calculation element e i and e j The correlation strength G ij , a design element relationship diagram is generated, where w1 and w2 are the parameters for adjusting the influence of the dependency strength and influence difference, respectively, and w3 is the adjustment parameter for the influence of the element attribute difference.

3. The intelligent creative method based on design elements according to claim 2, characterized in that: The analysis steps of users’ emotional responses to design elements in the differentiated cultural background are as follows: Based on the design element relationship diagram, combined with user comment data, emotional vocabulary is mapped and the formula is adopted. Calculate the association strength F between element i and sentiment word j ij , output the sentiment vocabulary mapping result, where G ik is the weight of the relationship between element i and element k, r kj is the association frequency of element k with sentiment word j in user comments, a is the adjustment index used to enhance or weaken the influence of frequency, λ is the smoothing parameter used to adjust the influence of distance attenuation, and d kj is the distance attenuation factor between elements, and n represents the number of design elements; According to the sentiment vocabulary mapping result, the formula is adopted: Calculate the sentiment preference score C of the kth cultural background k , generate sentiment preference analysis results, where b is the exponential transformation of sentiment intensity, c i is the cultural weight factor, h ik is a reconciliation factor used to balance the impact of different cultures. ik is the sentiment mapping score under the kth cultural background, and m is the type of different cultural backgrounds; Using the sentiment preference analysis results, we integrate them and use the formula: Calculate the weighted sentiment preference index P and output the sentiment preference overview, where v k is the comprehensive importance of the k-th cultural background, which is used to provide a weighted consideration of different cultural backgrounds.

4. The intelligent creative method based on design elements according to claim 3, characterized in that: The steps for obtaining the cultural preference clustering results are: Based on the sentiment preference overview, user reviews are aggregated using the formula, Calculate the aggregated user evaluation index D and obtain the aggregated evaluation result, where u i is the weight of the i-th user, which is used to adjust the influence of user evaluation, P i is the sentiment preference index of the i-th user, ln(P i +1) is used to smooth extreme values, and p represents the number of users; According to the aggregated evaluation results, sentiment categories are divided using the formula: Calculate the normalized sentiment category score Z to obtain the sentiment category division result, where max(D) represents the maximum value of the aggregated user evaluation index; Based on the emotion classification results, the formula is adopted: Calculate the comprehensive cultural preference index H and obtain the cultural preference clustering result, where μ k is the influence coefficient of the kth culture, which is used to adjust the contribution of different cultures to the clustering results, and m represents the types of different cultural backgrounds.

5. The intelligent creative method based on design elements according to claim 4, characterized in that: The adjustment steps of the design elements are: To analyze the cultural preference clustering results, the formula is used: Calculate the comprehensive preference weight W of the i-th culture i , we get the comprehensive analysis results of cultural preferences, where h k is the cluster weight of preference k in the ith cultural background, p k is the influence coefficient of preference k, N represents the cultural preference type; Based on the comprehensive analysis results of the cultural preferences, combined with user feedback, the design elements are adjusted and the formula is adopted. Calculate the adjusted design element value Y′, where Y is the original design element set and λ Y is an adjustment factor used to enhance the impact of user feedback, f j is the data about element j in user feedback, W j is the comprehensive preference weight of the jth culture, and m represents the types of different cultural backgrounds; According to the adjusted design element values, the design element adjustment contents and expected effects are integrated and recorded to obtain the adjusted design element results.

6. The intelligent creative method based on design elements according to claim 5, characterized in that: The steps for obtaining the dynamic adaptive design solution are: Based on the adjusted design element results, the user interaction data is analyzed and the formula is used. Calculate the user interaction index I to evaluate the effectiveness of the design, where L i is the interactive data indicator, e′ i is the adjusted design element, l is the number of adjusted design elements; Update the design template using the user interaction metric, using the formula, T=τ T ·Q+μ T ·I Calculate the comprehensive score T of the updated design template and output the optimized design template, where τ T and μ T is the adjustment coefficient, Q is the template configuration score obtained from the comparison of historical cases; According to the optimized design template, combined with market and user data, the changing market demands are matched to generate a dynamic adaptive design solution.

7. The intelligent creative method based on design elements according to claim 6, characterized in that: The steps for obtaining the final intelligent creative solution of the design element are: Applying the dynamic adaptive design scheme, using the formula, Calculate the evaluation score K and get the preliminary evaluation result, where X i is the i-th element in the design, α i is the weight factor that adjusts the impact of each design element, d i is the nonlinear coefficient used to adjust the influence of the element, and n represents the number of design elements; Based on the preliminary evaluation results, simulations were conducted to analyze the user experience and the formula was used. Calculate the user experience score U and get the simulation results, where κ j is the weight coefficient of each element in the simulation, which is used to adjust the impact of user experience, r j is a nonlinear adjustment coefficient used to simulate complex user interaction effects, and M is the total number of user ratings; Combine the simulation results and preliminary evaluation results, balance the evaluation score and user experience score, optimize the overall effect and market adaptability of the design solution, and output the final intelligent creative solution of the design elements.

8. Intelligent creative system based on design elements, characterized by: According to any one of claims 1 to 7, the intelligent creative method based on design elements comprises: The element analysis module collects design elements, analyzes the dependency strength between elements, scores the influence of each design element, combines it with element attributes, calculates the correlation strength between elements, and generates a design element relationship diagram; The sentiment mapping module maps sentiment vocabulary based on the design element relationship diagram and combines user comment data, calculates the sentiment preference score of the cultural background, and integrates and outputs a sentiment preference overview; The sentiment clustering module aggregates user comments according to the sentiment preference overview, divides the sentiment categories and calculates the normalized sentiment category scores, analyzes the comprehensive cultural preference indicators, and obtains the cultural preference clustering results; The preference adjustment module analyzes the cultural preference clustering results, calculates the comprehensive preference weight of the culture, adjusts the design elements in combination with user feedback, integrates and records the design element adjustment content and expected effects, and obtains the adjusted design element results; The template update module analyzes user interaction data and calculates user interaction indicators according to the adjusted design element results, uses the user interaction indicators to update the design template, combines market and user data, matches market change needs, and generates a dynamic adaptive design solution; The design optimization module applies the dynamic adaptive design solution, calculates the evaluation score, performs simulation, analyzes the user experience, balances the evaluation score and the user experience score, optimizes the design solution, and outputs the final intelligent creative solution of the design elements.

Images