A method for measuring the aesthetic appeal of automotive exterior design based on morphological and energy efficiency aesthetics.

Abstract

This invention discloses a method for measuring automotive exterior aesthetics based on morphological and energy efficiency aesthetics, relating to the field of automotive design technology. The method includes: data collection and preprocessing, including the collection and preprocessing of 3D automotive model data and energy efficiency review data; calculating automotive morphological aesthetics based on automotive morphological complexity and morphological order; calculating automotive energy efficiency aesthetics based on automotive energy efficiency complexity and energy efficiency order; calculating automotive exterior aesthetics by weighted summation of the morphological and energy efficiency aesthetics; and verifying the automotive exterior aesthetics using a nine-level Likert scale and Spearman's rank correlation coefficient. This invention, through scientific calculation methods and verification techniques, achieves numerical quantification of automotive exterior aesthetics, improves the efficiency and quality of automotive exterior design, and promotes innovative development in the field of automotive design.

Description

Technical Field

[0001] This invention relates to the field of automotive design and evaluation technology, and in particular to a method for measuring the aesthetic appeal of automotive appearance based on morphological beauty and energy efficiency. Background Technology

[0002] With the continuous advancement of technology, especially the rapid development of artificial intelligence, the automotive design field has ushered in a new era of intelligent design. Traditional automotive exterior design mainly relies on the designer's experience and subjective aesthetics, lacking scientific and quantitative evaluation standards.

[0003] Current research has attempted to apply aesthetic measurement theory and information entropy to automotive appearance evaluation, but most of these studies remain at the theoretical level and lack practical application verification. Furthermore, existing evaluation methods often focus on specific aspects, such as morphological aesthetics or energy efficiency aesthetics, lacking a comprehensive evaluation of automotive appearance aesthetics. Therefore, establishing a scientific and objective evaluation system for automotive appearance aesthetics has become an urgent problem to be solved in the current automotive design field. Summary of the Invention

[0004] The purpose of this invention is to propose a method for measuring the aesthetic appeal of automotive exterior design based on morphological and energy-efficiency aesthetics. Through scientific calculation methods and verification means, this method achieves numerical quantification of automotive exterior aesthetics, thereby promoting innovative development in the field of automotive design.

[0005] To achieve the above objectives, this invention proposes a method for measuring the aesthetic appeal of automotive exterior design based on morphological and energy efficiency aesthetics. The specific steps are as follows:

[0006] S1. Data collection, including 3D model data of automobiles and energy efficiency review data, and preprocessing the 3D model data of automobiles and the energy efficiency review data;

[0007] S2. Calculate the aesthetics of car form based on the complexity and order of car form.

[0008] S3. Calculate the aesthetics of vehicle energy efficiency based on vehicle energy efficiency complexity and vehicle energy efficiency order;

[0009] S4. Calculate the vehicle's appearance aesthetics by weighted summing of the vehicle's morphological aesthetics and its energy efficiency aesthetics.

[0010] S5. The aesthetics of the car's exterior were verified using a nine-level Likert scale and Spearman's rank correlation coefficient.

[0011] Preferably, in S1, the preprocessing of the 3D car model data includes: view mode switching, background graying processing, and normalization processing; the preprocessing of the energy efficiency review data includes: data cleaning, text normalization, word segmentation, word frequency statistics, and LDA topic summarization.

[0012] Preferably, in S2, the formula for calculating the aesthetic appeal of the vehicle's form is as follows:

[0013]

[0014] Among them, M s For the aesthetics of car form, O s For the order of automobile form, C s For the complexity of the car's shape.

[0015] Preferably, the complexity C of the vehicle's shape s The rank, energy dissipation, and slow growth rate of the system exhibit complex states under the complex interactions of the system, and their calculation formulas are as follows:

[0016] C s =r s ×e×t;

[0017] Where, r s Let E be the dimension of the linear vector space of the car's exterior structure, E be the energy dissipation of the car's exterior, and t be the slow growth rate.

[0018] Using information entropy theory, the morphological order O of the car is calculated. s The formula is as follows:

[0019]

[0020] Among them, O s For the order of automobile form, f j (x i ) represents the function for the exterior structural lines of a car, W j Let be the weight of the structure line j, m be the number of points on the curve with different absolute values ​​of their derivatives, and k = (ln m). -1 It can satisfy 0≤S j ≤1; a=1, 2, ···, 5, corresponding to the outline, front view, side view, rear view, and top view respectively. Figure 5 There are three car exterior views, where j is an integer and i is an integer.

[0021] Preferably, the weight W of the structural line j j The calculation formula is as follows:

[0022]

[0023] Among them, w fj w represents the weight of the eye-tracking data for the number of fixations of the j-th curve. tj represents the weight of the fixation duration eye-tracking data for the j-th curve.

[0024] Preferably, in S3, the formula for calculating the vehicle's energy efficiency is as follows:

[0025]

[0026] Among them, M e For automotive energy efficiency, O e For the sake of automotive energy efficiency order, C e Complexity of automotive energy efficiency.

[0027] Preferably, the vehicle energy efficiency complexity C e The calculation formula is as follows:

[0028] C e =r e ;

[0029] Where, r e Let be the dimension of the energy efficiency vector space;

[0030] Using the Gibbs free energy function, the energy efficiency order O of the vehicle is calculated. e The formula is as follows:

[0031]

[0032] Where p represents energy efficiency, O e For energy efficiency order, S p For energy efficiency entropy, W p Let q be the weight of energy efficiency p, where q is an integer;

[0033] The weight W of the energy efficiency p p The calculation formula is as follows:

[0034]

[0035] Among them, f p For word frequency.

[0036] Preferably, the energy efficiency entropy in, The formula for calculating the intensity value of vehicle energy efficiency experience is as follows:

[0037]

[0038] in, This is the p-th positive energy efficiency experience term; C is the p-th negative term for energy efficiency experience; δ Let ε be the δth degree level, where δ is an integer; δ The frequency of the degree adverb at the δth degree level of the positive polarity word for energy efficiency experience; θ δ The frequency of degree adverbs at the δth degree level of negative polarity words in energy efficiency experience; ΔG pΔH is the sum of the products of positive energy efficiency experience terms and their emotional intensity in the review data; p It is the absolute value of the sum of the products of positive energy efficiency experience words and their emotional intensity in the comment data, plus the sum of the products of negative energy efficiency experience words and their emotional intensity.

[0039] Preferably, in S4, the formula for calculating the aesthetic appeal of the car's exterior is as follows:

[0040]

[0041] Where M represents the aesthetics of the car's exterior, and W... s Weighting of automotive aesthetics, W e Weighting of vehicle energy efficiency.

[0042] Preferably, the weight W for the aesthetic appeal of the vehicle form s And the weighting of automotive energy efficiency W e The weighting is based on the G1 expert weighting method, which quantifies and scores the relative importance of adjacent indicators to determine the importance weight of each indicator. Let the most important indicator be U1, and the indicators be ranked according to importance as U2, U3, ..., U1. n The calculation formula is as follows:

[0043]

[0044]

[0045] Where τ is an integer, r is an integer n For U n-1 with U n The ratio of importance.

[0046] Therefore, this invention proposes a method for measuring the aesthetic appeal of automotive exteriors based on morphological beauty and energy efficiency beauty, with the following beneficial effects:

[0047] (1) This invention combines aesthetic measurement theory, information entropy theory and complexity theory, and systematic analysis of automotive appearance aesthetic evaluation theory and methodology, and refines an automotive appearance aesthetic measurement model that combines morphological beauty measurement and energy efficiency beauty measurement. This overcomes the shortcomings of traditional evaluation methods, which are highly subjective and difficult to standardize, and improves the scientificity and objectivity of the evaluation results.

[0048] (2) This invention combines eye-tracking experiments, information entropy calculation and G1 expert weighting method to propose a scientific and systematic method for calculating aesthetics, which has high practical value.

[0049] (3) The method of measuring aesthetics based on morphological aesthetics and energy efficiency aesthetics of the present invention can also be extended to the evaluation of appearance design of products in other fields, and has wide applicability and promotion value.

[0050] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a method for measuring the aesthetic appeal of an automobile's exterior based on morphological and energy-efficiency aesthetics, according to the present invention.

[0052] Figure 2 This is a diagram showing the location distribution of automotive exterior design elements in a method for measuring automotive exterior aesthetics based on morphological and energy-efficiency aesthetics, as described in this invention.

[0053] Figure 3 This is an eye-tracking experiment flowchart of a method for measuring the aesthetic appeal of automobile exteriors based on morphological and energy-efficiency aesthetics, according to the present invention.

[0054] Figure 4 This is a schematic diagram of a questionnaire for a survey on the aesthetics of an automobile's exterior, based on a method for measuring the aesthetics of an automobile's exterior based on morphological aesthetics and energy efficiency aesthetics, according to the present invention.

[0055] Figure 5 This is a schematic diagram of the perplexity calculation results of the noun segmentation set in the automobile appearance aesthetic measurement method based on morphological aesthetics and energy efficiency aesthetics of the present invention.

[0056] Figure 6 This is a schematic diagram of the morphological order of various views of the exterior of 20 sample cars, based on the method for measuring the aesthetic appeal of car exteriors according to the present invention, which is based on morphological aesthetics and energy efficiency aesthetics.

[0057] Figure 7 This is a distribution chart of scores for 20 sample cars based on the method for measuring the aesthetic appeal of car appearance based on morphological and energy-efficiency aesthetics according to the present invention. Detailed Implementation

[0058] To make the technical solutions, advantages, and objectives of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below. The described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the protection scope of this application.

[0059] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0060] like Figure 1As shown, this invention provides a method for measuring the aesthetic appeal of automotive exteriors based on morphological beauty and energy efficiency beauty. The specific steps are as follows:

[0061] 1. Data Collection and Preprocessing

[0062] 1.1 Vehicle Model Data Collection

[0063] A research sample set was constructed based on sedan sales volume, specifically the top 100 best-selling sedan models from the "Autohome" website, to ensure sufficient data for the study. Data collection involved randomly sampling 20 models from the sample set to form the research dataset. The dataset included: 3D car model data and energy efficiency review data (user reviews crawled from Autohome and Dongchedi websites). First, the 3D car model data was used as the research data for calculating the complexity and order of car morphology. Second, the energy efficiency review data was used as the research data for calculating the energy efficiency complexity and order of car exterior design.

[0064] 1.2 Data Preprocessing

[0065] 1.2.1 Preprocessing of 3D car model data, the steps are as follows:

[0066] (1) Import the sample car 3D scale simulation model from www.dongchedi.com into Rhino software, switch the view mode to pen mode, and generate a 3D line drawing model.

[0067] (2) Using the perspective switching function of Rhino software, generate the front view, side view, rear view, and top view. Figure 4 Line drawing of each view.

[0068] (3) As shown in Table 1, according to the automotive exterior design element guidelines, map the automotive exterior design elements to the corresponding views; Figure 2 As shown, the line drawings of the four views were imported into Adobe Illustrator software for standardization. The background of the views was grayed out (R:172, G:172, B:172), the line style of the car model line drawing in the views was black (R:0, G:0, B:0), and the car model itself was filled with white (R:255, G:255, B:255). This was done to eliminate the influence of factors such as color and material, so as to achieve standardized car exterior element line drawings. The line drawings are shown in Table 2.

[0069] Table 1. List of automotive exterior design elements extracted in this paper.

[0070]

[0071]

[0072]

[0073] Table 2 Automotive Appearance Preprocessing Sketch

[0074]

[0075]

[0076] (4) According to the logic of calculating the automotive form order, the sketch is divided into five parts: the first part is the outline view, the second part is the front view, the third part is the side view, the fourth part is the rear view, and the fifth part is the top view.

[0077] 1.2.2 Preprocessing of Energy Efficiency Evaluation Data, steps are as follows:

[0078] (1) Data cleaning, use the Excel data filter to remove data noises including special characters, non-semantic related symbols, duplicate comments, invalid comments, etc. in the text.

[0079] (2) Text normalization, normalize the energy efficiency evaluation data, and perform related stop word removal processing. Specifically, use the Micro Word Cloud software to perform stop word removal processing on the massive comment data, including removing meaningless prepositions, verbs (such as "de", "shi", "zai"...), brand institution nouns and other stop words.

[0080] (3) Word segmentation, perform word segmentation on the normalized energy efficiency evaluation. Specifically, use the jieba word segmentation algorithm of the Micro Word Cloud software to split the relevant text data into individual words. Finally, construct a noun word segmentation collection and an adjective word segmentation collection of the energy efficiency comment data, further count the number of adjective feature words and group similar feature words.

[0081] (4) Word frequency statistics, use the word frequency statistics tool of the Micro Word Cloud software to perform word frequency statistics on the grouped adjectives. As shown in Table 3, sort according to the frequency from high to low to prepare for the subsequent calculation of the energy efficiency order.

[0082] Table 3 Adjective Word Frequency Statistics (Top 50 Adjectives)

[0083]

[0084]

[0085] (5) LDA Topic Induction, based on the LDA topic model, cluster and induce the topic feature word collection; first use the perplexity model to calculate the number of topics in the noun word segmentation collection in the comment data, such as Figure 3As shown, as the number of topics increases, the perplexity gradually decreases and tends to stabilize, thus determining the number of noun topics in the comment data; then, the general parameter settings of the LDA model are determined; finally, the probability of noun topic words in the comment data is calculated based on the LDA model combined with the Gibbs sampling iterative algorithm, and the energy efficiency complexity is determined based on the calculated noun topic words.

[0086] 2. Calculation of car exterior aesthetics

[0087] 2.1 Calculation of Automobile Aesthetics

[0088] Based on the formula for automotive aesthetics, the aesthetics of automotive form are calculated. The calculation formula is as follows:

[0089]

[0090] (1) Calculate the morphological complexity C of the vehicle s =r s ×E×t,r s It is the dimension of the linear vector space of the car's exterior structure. Based on the principle of minimal complexity, r s =3; Since this study only involves the aesthetic measurement of automobile appearance and does not involve the iteration and improvement of automobile appearance, E=1, t=1.

[0091] (2) Calculate the morphological order of automobiles

[0092] First is W j The calculation divides the sample car line drawing into outer contour view, front view, side view, rear view, and top view, and calculates W for each view. j Eye-tracking experiments were conducted on different views. Data collection was based on the number of fixations and fixation duration. The experimental steps are as follows:

[0093] 1) Selection of experimental subjects. College students were randomly selected as subjects, regardless of gender or age. They were required to have myopia of less than 500 degrees, no color blindness or color weakness, and no neurological diseases.

[0094] 2) Experimental Environment. This experiment was conducted in the Human-Computer Interaction Laboratory of Shenyang Aerospace University. The laboratory environment fully met the requirements of the experiment: the overall color scheme of the experimental space was gray; the experimental tabletop was clean and free of clutter; the illuminance of the experimental work surface was set at 120-150 lux, with a tri-color light source and a color temperature of 5000K, and no natural light; the laboratory had noise shielding capabilities, and the indoor noise level was below 30 dB.

[0095] 3) Experimental Equipment and Materials. The equipment used was the Tobii Pro Lab integrated platform, including a Tobii ProGlasses 3 wearable eye tracker (compatible with prescription lenses, maximum 500°, sampling frequency of 100Hz, and a measurement deviation of 0.5 degrees from the actual eye movement position) and a PC testing computer (DELL Latitude 3420 laptop with an external monitor, model PHL 2751, 27-inch screen, 2560×1440 resolution, Windows 10 operating system). The preprocessed car view from 3.1.1 (car model data) was used as the experimental material.

[0096] 4) Experimental testing procedures. For example... Figure 4 As shown, firstly, the experimental equipment was debugged, the experimental materials were input into the PC testing computer, the subject information was filled in, and the experimental instructions were read. Emphasis was placed on the subject's proper sitting posture and the correct wearing of the eye tracker, limiting the distance between the subject's eyes and the testing monitor to 70cm. In the car outline drawing experiment phase: subjects observed the test card for one-point calibration. After gaze correction, subjects first observed a specific observation point in the black view (observation time 5000ms), then observed the subject material (observation time 10000ms). The page switching speed was set to 50ms, and the above observation process was repeated until the observation of the sample experimental materials was completed. In the car four-view drawing experiment phase: except for the observation time of the subject material being 20000ms, everything else remained the same.

[0097] 5) Data Collection. After the experiment, the experimental data on the SD card of the eye tracker was imported into the PC testing computer. The eye movement index data (number of fixations and fixation duration) of all subjects were collected using the pre-installed Pro Lab software on the PC testing computer, and further data analysis was carried out in conjunction with Excel.

[0098] 6) Data statistical analysis: First, calculate the weight of each eye-tracking data point for each structural line in the view: Where w fj The weights of the eye-tracking data for the number of fixations of the j-th curve are represented by these weights. Where w tj The weights of the fixation duration eye-tracking data for the j-th curve are then represented; subsequently, the importance weights of each structural line in the view are calculated: Among them W αj Let the importance weight be represented as the weight of the j-th curve in the α-th view.

[0099] Eye-tracking experimental data and W from the outer contour view, front view, side view, rear view, and top view of the sample car line drawing. j The weighting is shown in Tables 4-8.

[0100] Table 4. Eye-tracking experimental data of car outline and W j Empowerment

[0101]

[0102]

[0103] Table 5. Eye-tracking experimental data and W for the front view of the car. j Empowerment

[0104]

[0105] Table 6. Eye-tracking experimental data and W for car side view. j Empowerment

[0106]

[0107]

[0108]

[0109] Table 7. Eye-tracking experimental data and W for rear-view car view j Empowerment

[0110]

[0111]

[0112] Table 8. Eye-tracking experimental data for car top view and W j Empowerment

[0113]

[0114]

[0115] The next step is to calculate the information entropy of the j-th structural line on the car's exterior. The steps are as follows:

[0116] 1) Import the pre-processed car exterior line art into Rhino 8 software. Use the curve tool to construct the car exterior structure lines proportionally (model size in millimeters). (Due to the high symmetry of the car exterior, only half of the exterior structure lines are selected based on the central axis of symmetry for the front, rear, and top views). Then, use a derivative calculation method based on curve parametric representation (Grasshopper plugin) to calculate the derivative of the j-th structure line. The specific steps are as follows: Select and import the j-th structure line into the Curve component; use the Divide Distance component to differentiate the structure line by limit equidistant differentiation to obtain discrete points; use the Derivatives component to calculate the derivative of each point on the structure line; use the Deconstruct Vector component to split the derivative vector into x and y components (two-dimensional curve); use the Division component to calculate the derivative of each node and import the data into Excel software.

[0117] 2) After importing the derivative data into Excel, use the data analysis tools in the software according to the formula. Calculate the information entropy of the j-th structural line on the car's exterior.

[0118] like Figure 5 As shown, the order of the car's exterior morphology is calculated by weighted summation of the information entropy redundancy of each structural line using Excel software. The calculation formula is as follows:

[0119]

[0120] (3) Calculate the aesthetics of car form

[0121] Based on the importance weights and information entropy redundancy values ​​of the automotive exterior structural lines, the aesthetic appeal of the car's form was calculated using data analysis tools in Excel software. The calculation formula is as follows:

[0122]

[0123] The results of ranking the aesthetic appeal of automobiles are shown in Table 9.

[0124] Table 9. Ranking of the aesthetic appeal of the 20 sample cars.

[0125] Rank Sample car Aesthetic Form Rank Sample car Aesthetic Form 1 hq* 0.9835 11 pst* 0.9376 2 bm* 0.9738 12 sy* 0.9353 3 xp* 0.9667 13 xr* 0.9337 4 bc* 0.9613 14 yg* 0.9317 5 wl* 0.9543 15 zj* 0.922 6 wew* 0.9512 16 han* 0.9122 7 ad* 0.9483 17 hb* 0.8966 8 jk* 0.9464 18 ylt* 0.8907 9 tsl* 0.9435 19 st* 0.8751 10 xm* 0.9415 20 kmr* 0.8419

[0126] 2.2 Calculation of Vehicle Energy Efficiency Ratio

[0127] First, calculate the vehicle energy efficiency complexity C. e =r e r e It is the dimension of the energy efficiency experience vector space during vehicle operation, that is, the number of energy efficiency experiences is equal to r. e(Determined based on LDA noun theme summarization results).

[0128] Secondly, calculate the energy efficiency order of automobiles. The specific steps are as follows:

[0129] 1) Assigning values ​​to energy efficiency experience word pairs (adjective pairs). Based on the dimension of the energy efficiency experience vector space, energy efficiency experience word pairs are determined according to the word frequency ranking of the adjective segmentation set, and values ​​are assigned to the determined energy efficiency experience word pairs. As shown in Table 10, a set of energy efficiency experience word pairs contains one word with a positive emotional polarity and one word with a negative emotional polarity. The positive polarity word is assigned a value of +1, and the negative polarity word is assigned a value of -1. This serves as a criterion for further measuring the emotional intensity of energy efficiency experiences.

[0130] Table 10 Energy Efficiency Terms

[0131]

[0132] 2) Measurement of the emotional intensity of energy efficiency experience. The emotional intensity of energy efficiency experience word pairs is measured based on degree adverb data. Degree adverbs modify adjectives in terms of degree and are generally located before or after the modified adjective, such as "very," "extremely," and "quite." Different words express different levels of tone. The intensity is assigned to these adverb levels and their corresponding semantic nuances using the How Net dictionary, as shown in Table 11.

[0133] Table 11 Relationship between degree adverbs and intensity assignment

[0134]

[0135] 3) Calculate the intensity value of vehicle energy efficiency experience. The formula is expressed as:

[0136]

[0137] in This indicates the p-th positive term representing energy efficiency experience; Indicates the p-th negative term for energy efficiency experience; C δ ε represents the δ-th degree level, where δ = 1, 2, ..., 7; δ The frequency of degree adverbs indicating the δth degree level of positive energy efficiency experience, θ δ The frequency of degree adverbs indicating the δth degree level of negative energy efficiency experience. ΔG p ΔH represents the sum of the products of positive energy efficiency experience words and their emotional intensity in the review data. p It is represented as the absolute value of the sum of the products of positive energy efficiency experience words and their emotional intensity in the comment data, plus the sum of the products of negative energy efficiency experience words and their emotional intensity.

[0138] 4) Calculate the weight W of the vehicle energy efficiency term pair. p As shown in Table 12, based on the frequency of each energy efficiency experience word pair, a frequency-weighted calculation is performed on the energy efficiency experience word pairs. The result is equal to the weight W of each energy efficiency word pair. p (There are q pairs of energy efficiency experience terms, and the frequency of each term pair p is f.) p ,but

[0139] Table 12 Weighting of Each Energy Efficiency Experience Term

[0140]

[0141]

[0142] Finally, calculate the vehicle's energy efficiency aesthetics score. Determine the intensity value of the vehicle's exterior energy efficiency experience. And the weight W of the energy efficiency term p Then, through the formula The vehicle energy efficiency score was calculated and ranked. The results are shown in Table 13.

[0143] Table 13 Ranking of Vehicle Energy Efficiency

[0144] Rank Car models Mido Rank Car models Mido 1 kmr* 0.2944 11 hq* 0.2809 2 sy* 0.2854 12 zj* 0.2798 3 st* 0.2850 13 ylt* 0.2787 4 wl* 0.2848 14 pst* 0.2779 5 xm* 0.2842 15 tsl* 0.2776 6 hb* 0.2828 16 han* 0.2720 7 bm* 0.2828 17 bc* 0.2713 8 xr* 0.2825 18 yg* 0.2710 9 jk* 0.2824 19 xp* 0.2668 10 ad* 0.2820 20 wew* 0.2598

[0145] 2.3 Weighted Calculation of Vehicle Aesthetic Appeal and Vehicle Energy Efficiency

[0146] The weighting of automotive aesthetics (W) was determined using the G1 expert weighting method. s (W) and the weighting of vehicle energy efficiency (W) e Weighting is performed. The principle behind this method is to quantify and score the relative importance of adjacent indicators, thereby determining the importance weight of each indicator. Let the most important indicator be U1, then the indicators ranked by importance are denoted as U2, U3, ..., U... n r n For U n-1 with U n The importance ratio and the indicator importance rating scale are shown in Table 14.

[0147] Table 14 Importance Rating Scale for Indicators

[0148] <![CDATA[r n ]]> <![CDATA[Indicator U n-1 Compared with indicator U n as compared to]]> 1.0 Equally important 1.2 Slightly important 1.4 Obviously important 1.6 Strongly important 1.8 Extremely important

[0149] To ensure the rationality and scientific nature of the weighting, 15 experts from five fields—automotive design, vehicle engineering, industrial design, ergonomics, and market management—were invited to conduct comprehensive weighting. The weighting results are shown in Table 15. The final weight W for morphological aesthetics was calculated. s The energy efficiency weighting is 0.6269, which is W. e It is 0.3731; Ws and W e The calculation formula is as follows:

[0150]

[0151] Where τ = 1, 2, ..., Indicates the number of experts;

[0152] Table 15 GI Expert Empowerment

[0153]

[0154]

[0155] 2.4 Calculation of Automobile Exterior Aesthetics

[0156] The aesthetic appeal of each sample car is calculated by weighting and summing the aesthetic appeal of its form and energy efficiency. The calculation formula is as follows:

[0157]

[0158] The aesthetic scores were sorted from largest to smallest to obtain the aesthetic evaluation dataset of the research samples, as shown in Table 16.

[0159] Table 16 Ranking of Overall Aesthetics of 20 Sample Cars

[0160]

[0161] 3. Verification of Mido Calculation

[0162] The results of the Meidu calculation were verified using questionnaire data, which also validated the research hypothesis of this paper, demonstrating the significance of this study. The specific steps are as follows:

[0163] (1) Questionnaire design. For example... Figure 6 As shown, a questionnaire was constructed using a 9-level Likert scale for 20 sample cars. The aesthetic level was designed from smallest to largest as follows: extremely unattractive, very unattractive, unattractive, somewhat unattractive, neutral, somewhat attractive, attractive, very attractive, and extremely attractive.

[0164] (2) Questionnaire distribution. This study used the "Credamo Data" platform (www.credamo.com) to manually distribute 400 questionnaires over a period of 3 days. The survey targets car enthusiasts on various internet platforms (users of Autohome forum, Dongchedi forum, Pacific Auto Network forum, and Weibo car topic users) to ensure that the surveyed group had a thorough understanding of cars and to guarantee the accuracy of the questionnaire data.

[0165] (3) Questionnaire collection and organization. For example... Figure 7 As shown, after collecting all questionnaires, invalid questionnaires (including those with missing data, uniform answers, those not filled out according to requirements, and those with too short a time to fill out) need to be screened out. The valid questionnaire data are then compiled into Excel software, and a score distribution chart is drawn.

[0166] (4) Questionnaire reliability analysis. First, the Cronbach's Alpha value of the valid questionnaire data was calculated. Based on the item independence characteristics and global consistency requirements of the questionnaire in this study, the classic Cronbach's Alpha formula was used to judge the reliability of the questionnaire scores. 0 indicates unreliable; 1 indicates completely reliable; below 0.6 indicates poor reliability; above 0.7 indicates good reliability. The analysis results are shown in Table 17. The classic Cronbach's Alpha formula is:

[0167]

[0168] Where: α represents Cronbach's alpha value, and N represents the number of items in the questionnaire. It is the variance of the i-th item in the questionnaire. It is the variance of the total score for all items for each respondent.

[0169] Table 17 Analysis of Questionnaire Data for 20 Car Models

[0170]

[0171]

[0172] (5) Validation of the aesthetic score calculation. The average aesthetic score of each car's exterior was calculated using a reliable questionnaire and used as the overall aesthetic score of the car exterior survey. The overall aesthetic scores from the questionnaire were ranked and compared with the ranking of the aesthetic scores of each sample car calculated by the aesthetic measurement model to complete the validation of the aesthetic score calculation. During the comparison and validation process, the Spearman rank correlation coefficient was used to test the validation results (-1 indicates perfect negative correlation, 0 indicates perfect no correlation, and 1 indicates perfect positive correlation). The validation results are shown in Table 18. The formula for the Spearman rank correlation coefficient is:

[0173]

[0174] Where, ρ s It is the Spearman rank correlation coefficient, d i is the rank difference for each pair of observations (i.e., for each i, the difference in its rank between the two variables is calculated), and n is the total number of observations.

[0175] Table 18 Analysis of Questionnaire Ranking and Meidu Calculation Ranking

[0176]

[0177] Therefore, this invention proposes a method for measuring automotive appearance aesthetics based on morphological beauty and energy efficiency aesthetics. This method combines aesthetic measurement theory, information entropy theory, and complexity theory, along with a systematic analysis of automotive appearance aesthetic evaluation theory and methodology. It condenses a measurement model for automotive appearance aesthetics that integrates morphological beauty measurement and energy efficiency aesthetics measurement, overcoming the shortcomings of traditional evaluation methods such as strong subjectivity and difficulty in standardization, thus improving the scientific rigor and objectivity of the evaluation results. Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of this invention and not to limit it. Although the invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solution of this invention, and these modifications or equivalent substitutions should not cause the modified technical solution to deviate from the spirit and scope of the technical solution of this invention.

Claims

1. A method for measuring the aesthetic appeal of automotive exterior design based on morphological and energy-efficiency aesthetics, characterized in that, The specific steps are as follows: S1. Data collection, including 3D model data of automobiles and energy efficiency review data, and preprocessing the 3D model data of automobiles and the energy efficiency review data; S2. Calculate the aesthetics of car form based on the complexity and order of car form. S3. Calculate the aesthetics of vehicle energy efficiency based on vehicle energy efficiency complexity and vehicle energy efficiency order; S4. Calculate the vehicle's appearance aesthetics by weighted summing of the vehicle's morphological aesthetics and its energy efficiency aesthetics. S5. The aesthetics of the car's exterior were verified using a nine-level Likert scale and Spearman's rank correlation coefficient. In S2, the formula for calculating the aesthetic appeal of the vehicle's form is as follows: ； in, For the aesthetics of car form, For the order of automobile form, For the complexity of the car's form; In S3, the formula for calculating the vehicle's energy efficiency rating is as follows: ； in, For automotive energy efficiency, For the sake of automotive energy efficiency order, Complexity of automotive energy efficiency; In S4, the formula for calculating the aesthetics of the car's exterior is as follows: ； in, For the aesthetics of the car's exterior, Weighting of the aesthetic appeal of the car's form. Weighting of vehicle energy efficiency.

2. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 1, characterized in that, In S1, the preprocessing of the 3D model data of the car includes view mode switching, background graying processing and normalization processing; The energy efficiency review data preprocessing includes: data cleaning, text normalization, word segmentation, word frequency statistics, and LDA topic summarization.

3. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 1, characterized in that, The complexity of the vehicle's form The rank, energy dissipation, and slow growth rate of the system exhibit complex states under the complex interactions of the system, and their calculation formulas are as follows: ； in, Let be the dimension of the vector space of the automotive exterior structure lines. For the dissipation of energy in the car's exterior, A slow growth rate; Using information entropy theory, the morphological order of the aforementioned automobile is calculated. The formula is as follows: ； in, For the order of automobile form, For the function of automotive exterior structural lines, For structural lines The weights are given by m, where m is the number of points on the curve with distinct absolute values ​​of the derivative. ; It is an integer. It is an integer. It is an integer.

4. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 3, characterized in that, The structural line weight The calculation formula is as follows: ； in, For the first The weights of eye-tracking data for the number of fixations on each curve. For the first The weights of fixation duration eye-tracking data for each curve.

5. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 1, characterized in that, The complexity of automotive energy efficiency The calculation formula is as follows: ； in, Let be the dimension of the energy efficiency vector space; The energy efficiency order of the vehicle is calculated using the Gibbs free energy function. The formula is as follows: ； in, For energy efficiency, For energy efficiency order, For energy efficiency entropy, For energy efficiency The weight, It is an integer; The energy efficiency weight The calculation formula is as follows: ； in, For word frequency.

6. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 5, characterized in that, The energy efficiency entropy = ,in, The formula for calculating the intensity value of vehicle energy efficiency experience is as follows: ； in, For the first A positive term for energy efficiency experience; For the first A negative term for energy efficiency experience; For the first A degree level, It is an integer; For energy efficiency experience, positive polarity term The frequency of degree adverbs at each degree level; For energy efficiency experience, negative polarity words The frequency of degree adverbs at each degree level; This is the sum of the products of positive energy efficiency experience terms and their emotional intensity in the review data; It is the absolute value of the sum of the products of positive energy efficiency experience words and their emotional intensity in the comment data, plus the sum of the products of negative energy efficiency experience words and their emotional intensity.

7. The method for measuring the aesthetic appeal of automobile exterior design based on morphological and energy efficiency aesthetics according to claim 1, characterized in that, The weight of automotive aesthetics And the weight of automotive energy efficiency The weighting is based on the G1 expert weighting method, which quantifies and scores the relative importance of adjacent indicators to determine the importance weight of each indicator. Let the most important indicator be... Count them according to their importance. The calculation formula is as follows: ； ； in, It is an integer. It is an integer. for and The ratio of importance.

Images