Big data acquisition and analysis method and system based on costume design

Abstract

The invention relates to the technical field of costume design and big data analysis, and discloses a big data collection and analysis method and system based on costume design, and the method comprises the steps: obtaining multi-source heterogeneous data; a data quality evaluation algorithm and a cleaning technology are adopted; extracting a clothing image feature model; quantifying design elements of the clothing image features and analyzing element relevance; obtaining a manifold trend prediction result by adopting a time sequence prediction model based on LSTM and a multi-factor influence model; adopting a feature engineering method to obtain multi-dimensional user features; performing user preference clustering analysis; carrying out optimization, quality evaluation and screening on the candidate design schemes; a market performance prediction model based on the random forest is adopted for prediction; performing risk assessment; according to the invention, through application of the time sequence deep learning model, the complex change rule of the fashion trend can be captured, and accurate prediction of the future fashion trend is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of fashion design and big data analysis, more specifically, it relates to a big data collection and analysis method and system based on fashion design. BACKGROUND

[0002] With the rapid development of global fashion industry and the growing demand for personalized consumer, traditional fashion design mode is facing great challenges. Traditional design mainly relies on the subjective experience of designers and limited market research data, which has problems such as long design cycle, lagging market response, inaccurate grasp of consumer demand, etc. Especially in the fast fashion market, the fashion trend changes rapidly, and the traditional design method is difficult to keep up with the market rhythm, resulting in new product listing time lag, serious inventory accumulation and design homogenization.

[0003] In recent years, the wide application of big data technology in various industries has provided new opportunities for the transformation and upgrading of the fashion design industry. By collecting and analyzing massive consumer behavior data, fashion trend information, market sales data, etc., more scientific and accurate decision support can be provided for fashion design. However, the data in the field of fashion design has the characteristics of multi-source heterogeneity, strong real-time, and prominent subjectivity, and the existing big data analysis technology still has many deficiencies when applied to fashion design.

[0004] In the prior art, some research has tried to apply big data analysis to the field of fashion design, but there are generally problems such as limited data collection range, weak analysis method, low prediction accuracy, and insufficient personalization. Therefore, it is urgent to develop a big data collection and analysis method specifically for the characteristics of fashion design, which can effectively integrate multi-source data, accurately predict fashion trends, and realize personalized design recommendation, providing scientific technical support and decision basis for the fashion design industry. SUMMARY

[0005] The present application provides a big data collection and analysis method and system based on fashion design, which solves the technical problems of incomplete data collection, low trend prediction accuracy, and insufficient personalization in related technologies.

[0006] The present application provides a big data collection and analysis method based on fashion design, which includes: Obtain multi-source heterogeneous data, including e-commerce platform sales data, social media user-generated content, fashion website professional information, and environmental data; use data quality evaluation algorithm and cleaning technology on multi-source heterogeneous data to obtain standardized data set; Extract fashion image features and multi-dimensional user features from the standardized data set using feature engineering; quantify the design elements of fashion image features and analyze the element correlation to obtain fashion design element feature vector; The environmental data in the standardized data set is acquired, and a LSTM-based time series prediction model and a multi-factor influence model are input with the clothing design element feature vector and the environmental data to obtain a trend prediction result. The multi-dimensional user features are subjected to user preference clustering analysis to obtain a user preference mining result. The user preference mining result and the trend prediction result are input into a generative adversarial network to obtain a candidate design scheme, which is optimized, quality evaluated and screened to obtain a personalized design scheme. The personalized design scheme is subjected to market prediction and risk assessment to obtain a market performance pre-evaluation result and a risk control suggestion.

[0007] In a preferred embodiment, the acquisition process of the multi-source heterogeneous data specifically comprises: A distributed crawler cluster is constructed to monitor an e-commerce platform in real time, and a web crawler technology is used to acquire product description, price, sales, and user evaluation data to obtain e-commerce platform data; Based on the acquired e-commerce platform data, a keyword matching and topic tracking technology is used to acquire fashion user-generated content through a social media API interface call to obtain social media data; The e-commerce platform data and the social media data are data fused with professional information of a fashion website to obtain multi-source heterogeneous data.

[0008] In a preferred embodiment, the data quality evaluation algorithm and cleaning technology specifically comprises: The multi-source heterogeneous data is acquired, and the text data in the multi-source heterogeneous data is subjected to encoding format detection, and different detected encoding formats are uniformly converted into UTF-8 encoding; The image data in the multi-source heterogeneous data is subjected to format verification and size normalization processing; Based on rules and statistical methods, abnormal values in the processed multi-source heterogeneous data are detected, and detected price abnormalities, score abnormalities, and timestamp abnormalities are marked and removed to obtain a standardized data set.

[0009] In a preferred embodiment, the generation process of the clothing design element feature vector specifically comprises: The standardized data set is acquired, and a deep learning feature extraction technology is used to construct a clothing image feature extraction model for the standardized data set; A pre-trained ResNet network is used to extract basic visual features of the clothing image, and a clothing attribute recognition branch network is constructed based on the basic visual features to recognize design elements; A color feature vector is established, a style innovation degree index is defined by calculating the similarity difference between the design style and the historical popular style, and a clothing design element feature vector is obtained.

[0010] In a preferred embodiment, the generating of the fashion trend prediction result specifically comprises: Obtaining fashion design element feature vectors and environmental data, establishing a multi-factor influence model based on the fashion design element feature vectors and the environmental data, and comprehensively considering seasonal factors, economic factors, cultural event factors, and social media heat factors; Training the multi-factor influence model using an LSTM-based time series prediction model, setting a time window length and a prediction time length; Combining prediction models of different architectures to fuse the prediction results of each model using a weighted average method to obtain the fashion trend prediction result.

[0011] In a preferred embodiment, the generating of the user preference mining result specifically comprises: Obtaining the fashion trend prediction result, constructing a user behavior dataset based on the fashion trend prediction result, and the user behavior dataset including user browsing records, purchase records, evaluation records, and collection records; Analyzing the user behavior dataset using a collaborative filtering algorithm, calculating a user similarity matrix and an item similarity matrix; Constructing a user preference model based on the user similarity matrix and the item similarity matrix, dividing users into different preference groups through a clustering algorithm, and obtaining the user preference mining result.

[0012] In a preferred embodiment, the generating of the personalized design scheme specifically comprises: Obtaining the user preference mining result, constructing design constraints based on the user preference mining result, and the design constraints including cost constraints, material constraints, and process constraints; Optimizing and solving the design constraints using a genetic algorithm, setting a population size, a crossover probability, and a mutation probability; Evaluating the market adaptability and user satisfaction of the design scheme through a fitness function, selecting the final design scheme after multiple generations of evolution, and obtaining the personalized design scheme.

[0013] In a preferred embodiment, the generating of the market performance pre-evaluation result and risk control suggestion specifically comprises: Obtaining the personalized design scheme, constructing a market performance prediction model based on a random forest based on the personalized design scheme, and the market performance prediction model including sales prediction, user acceptance prediction, and market risk assessment; Performing multi-dimensional risk assessment on the market performance prediction model using a Monte Carlo simulation method, setting a simulation number and a confidence interval; Generating a decision support analysis report based on the multi-dimensional risk assessment result, obtaining the market performance pre-evaluation result and the risk control suggestion.

[0014] In a preferred embodiment, it also comprises: Based on the real-time feedback data of the personalized design scheme, a performance monitoring system is established, the accuracy is evaluated by comparing the real-time feedback data of the personalized design scheme with the market performance pre-evaluation result, and the market performance prediction model is updated by using online learning and incremental learning technology.

[0015] In a preferred embodiment, a big data collection and analysis system based on clothing design is used to execute the above-mentioned big data collection and analysis method based on clothing design, comprising: A data collection module is used to acquire multi-source heterogeneous data, including e-commerce platform sales data, social media user-generated content, fashion website professional information and environmental data; data quality evaluation algorithm and cleaning technology are used to obtain standardized data set; A feature extraction module is used to extract clothing image features and multi-dimensional user features by using feature engineering on the standardized data set; design elements of clothing image features are quantified and element correlation is analyzed to obtain clothing design element feature vector; A trend prediction module is used to acquire environmental data in the standardized data set, and clothing design element feature vector and environmental data are input into LSTM-based time series prediction model and multi-factor influence model to obtain popular trend prediction result; A user analysis module is used to perform user preference clustering analysis on multi-dimensional user features to obtain user preference mining result; A design generation module is used to input user preference mining result and popular trend prediction result into generative adversarial network to obtain candidate design scheme, and the candidate design scheme is optimized, quality evaluated and screened to obtain personalized design scheme; A market evaluation module is used to perform market prediction and risk assessment on the personalized design scheme to obtain market performance pre-evaluation result and risk control suggestion; An update optimization module is used to establish a performance monitoring system based on real-time feedback data of the personalized design scheme, compare the real-time feedback data of the personalized design scheme with the market performance pre-evaluation result to evaluate the accuracy, and update the market performance prediction model by using online learning and incremental learning technology.

[0016] The application has the beneficial effects that: by establishing a multi-source heterogeneous data collection network and a deep learning prediction model, the application can comprehensively consider multi-dimensional information such as seasonal factors, economic factors, cultural event factors, social media heat, and the like, and compared with a traditional prediction method, the prediction accuracy in each aspect of color trend, style trend, fabric trend and the like is improved; in particular, by application of a time series deep learning model, the complex change law of a popular trend can be captured, and accurate prediction of the future popular trend is realized, scientific trend guidance is provided for designers, and market risks of new product development are effectively reduced. By constructing a refined user portrait model and a design scheme generation mechanism based on a generative adversarial network, personalized design suggestions can be provided according to the characteristics and preferences of different user groups; not only the demographic characteristics and historical behaviors of users are considered, but also the potential preferences and social network influences of users are deeply mined, and a change from mass design to individual customization is realized; through a multi-objective optimization algorithm, while meeting the individualized needs of users, market adaptability, cost control and other business constraints are also considered, and user satisfaction and business feasibility of the design scheme are improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of the big data collection and analysis method based on clothing design in the application; Figure 2 is a module diagram of the big data collection and analysis system based on clothing design in the application; Figure 3 is a column chart of popular trend prediction accuracy comparison; Figure 4 is a line chart of user satisfaction improvement effect; Figure 5 is a radar chart of business effect improvement comparison. DETAILED DESCRIPTION

[0018] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is merely meant to provide a better understanding of the subject matter described herein and can include changes in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples can omit, substitute, or add various procedures or components as appropriate or desired. Additionally, the features described in some examples can also be combined in other examples.

[0019] At least one embodiment of the application discloses a big data collection and analysis method based on clothing design, as shown in Figure 1 , including: Step 1, acquire multi-source heterogeneous data, including e-commerce platform sales data, social media user-generated content, fashion website professional information, and environmental data; use data quality evaluation algorithm and cleaning technology on multi-source heterogeneous data to obtain standardized data set; Based on the diversified data needs of clothing design, a distributed data collection architecture is adopted to obtain a standardized clothing design data set.

[0020] Step 1.1, establish a multi-channel data collection network; Based on web crawler technology and API interface call, adopt multi-thread concurrent collection strategy to obtain commodity sales data from e-commerce platforms. Specifically, by building a distributed crawler cluster, real-time monitoring of clothing commodity information of major e-commerce platforms such as Taobao, Jingdong, Amazon, etc. is realized, including commodity description, price, sales volume, user evaluation data, etc. to obtain e-commerce platform data. At the same time, based on social media API interface, using keyword matching and topic tracking technology, fashion-related user-generated content on Instagram, Weibo, Xiaohongshu, etc. is obtained, and social media data is obtained. The e-commerce platform data and social media data are fused with the professional information of the fashion website to obtain multi-source heterogeneous data.

[0021] Step 1.2, implement data quality control and cleaning; Based on the collected multi-source heterogeneous data, use data quality evaluation algorithm to obtain data integrity and accuracy score. Perform encoding format detection and character standardization processing on text data, and unify different encoding formats of text to UTF-8 encoding. For image data, perform format verification and size normalization to ensure that the resolution and aspect ratio of the image meet the requirements of subsequent processing. Then, based on rules and statistical methods, detect outliers, including price anomalies, score anomalies, timestamp anomalies, etc. Label or exclude the detected abnormal data. By establishing a data quality evaluation index system, including integrity score, accuracy score and timeliness score, calculate the comprehensive data quality score according to the following steps: Calculate data integrity score: count the number of missing values in each field of the data set, calculate the proportion of missing fields in total fields, subtract the proportion from 1 to get the integrity score, the score range is 0 to 1, the value closer to 1 indicates the data is more complete.

[0022] Calculate data accuracy score: use cross-validation method to check the consistency of data, compare the consistency of the same information in different data sources, and calculate the proportion of accurate data in total data as the accuracy score, the score range is 0 to 1, the value closer to 1 indicates the data is more accurate.

[0023] Computing data timeliness score: According to the interval between data collection time and current time, a timeliness decay function is established, the longer the interval, the higher the score, the score range is 0 to 1, and the value closer to 1 indicates that the data is fresher.

[0024] Determine the weight coefficient: According to the quality requirements of different application scenarios, the weight coefficients of integrity, accuracy and timeliness are allocated respectively, the sum of the three weight coefficients is equal to 1, and the weight distribution can be dynamically adjusted according to actual needs.

[0025] Calculate the comprehensive score: Multiply the integrity score by its weight coefficient, multiply the accuracy score by its weight coefficient, multiply the timeliness score by its weight coefficient, then add the three weighted results to get the final comprehensive data quality score, the score range is 0 to 1.

[0026] Step 1.3, execute data standardization and format conversion; Based on the cleaned data, the data standardization processing technology is used to obtain the structured data set with unified format. Establish the standardization specification of clothing design data, including color coding standard, style classification system, fabric identification specification, etc. Map the data from different sources to a unified data mode. Through data format conversion and field mapping, information from different data sources can be seamlessly integrated.

[0027] Further, incremental data synchronization technology can be used instead of batch data processing mode. Based on message queue and streaming processing framework, real-time data stream processing technology is used to obtain quasi-real-time data update capability. This replacement embodiment can improve the real-time performance of data acquisition, better capture the rapidly changing fashion trends, and is particularly suitable for fast fashion brands that need to respond quickly to market changes.

[0028] Step 2, extract clothing image features and multi-dimensional user features from the standardized data set using feature engineering; quantify the design elements of clothing image features and analyze the element correlation to obtain the clothing design element feature vector; Based on the standardized clothing design data set, deep learning feature extraction technology is used to obtain the clothing design element feature vector.

[0029] Step 2.1, construct a clothing image feature extraction model; Based on the convolutional neural network architecture, a multi-layer feature extraction strategy is used to obtain multi-dimensional feature representation of clothing images. Through the pre-trained ResNet network, the basic visual features of the image are extracted, and then a special clothing attribute recognition branch network is constructed to recognize design elements such as color, style, pattern and fabric. The specific steps to establish the color feature vector are as follows: Image color space conversion: Convert the input RGB image to HSV color space to better separate color information and brightness information.

[0030] Color component extraction: Extract numerical values of each color channel from the converted image, including information of hue, saturation, and lightness.

[0031] Color intensity calculation: Calculate the intensity value of each color component in the entire image, which reflects the importance and proportion of the color in the image.

[0032] Feature vector construction: Arrange the intensity values of all color components in order to form a multi-dimensional vector, where each element of the vector represents the intensity of a color component, with a value range of 0 to 255.

[0033] Vector normalization: Normalize the constructed color feature vector to ensure the comparability of color features of different images.

[0034] Step 2.2, Establish a quantitative evaluation system of design elements; Based on the extracted visual features, use feature fusion and dimension reduction techniques to obtain the standardized quantitative representation of design elements. Define the style innovation degree index, and calculate the similarity difference between the design style and the historical popular style to measure the innovation degree: Historical style library construction: Collect and organize the feature vectors of all popular styles in history to establish a complete historical style database as a comparison benchmark.

[0035] Feature vector extraction: Extract features from the current design style to be evaluated to obtain its corresponding multi-dimensional feature vector representation.

[0036] Similarity calculation: Calculate the cosine similarity between the feature vector of the current design style and the feature vector of each style in the historical style library to obtain a series of similarity scores.

[0037] Maximum similarity determination: Find the maximum value from all calculated similarity scores, which represents the highest similarity between the current design and the historical style.

[0038] Innovation degree calculation: Subtract the maximum similarity value obtained in step four from one to obtain the final style innovation degree index, with a value range of 0 to 1, and the larger the value, the higher the innovation degree.

[0039] The specific implementation of the cosine similarity calculation function is: normalize the input two feature vectors A and B, then calculate the dot product of the two vectors, and divide by the product of the vector lengths, to get a similarity score with a value range of -1 to 1. Specifically, for vectors A and B, the similarity calculation is the inner product of vectors A and B divided by the product of the length of vector A and the length of vector B. This function can effectively measure the consistency of two design feature vectors in direction, and is not affected by the size of the vector.

[0040] Step 2.3: Construct a correlation analysis model for design elements; Based on the quantified design element characteristics, an association rule mining algorithm is used to obtain the association relationships between different design elements. By calculating the support and confidence of element combinations, high-frequency design element combination patterns are identified, providing a knowledge base for subsequent design scheme generation. The specific steps for establishing the element association strength matrix are as follows: Frequency of element occurrence: Traverse all design samples, count the total number of times each design element appears individually, and create an element frequency statistics table.

[0041] Statistical co-occurrence frequency of elements: Count the number of times any two design elements appear simultaneously in the same design sample, and establish an element co-occurrence frequency matrix.

[0042] Calculate the association strength: For any two elements, divide their co-occurrence frequency by the product of their individual occurrence frequencies to obtain the normalized association strength value.

[0043] Construct the association matrix: Arrange the association strength values ​​of all feature pairs according to the row and column correspondence to form a complete feature association strength matrix. The value of each element in the matrix ranges from 0 to 1.

[0044] Interpretation of correlation strength: The closer the value in the matrix is ​​to 1, the stronger the correlation between the two corresponding elements, and the more likely they are to appear simultaneously in the design; the closer the value is to 0, the weaker the correlation.

[0045] Furthermore, attention-enhanced feature extraction methods can be used to replace traditional convolutional neural networks. Based on the visual Transformer architecture, a self-attention mechanism is employed to obtain more accurate local design detail features. This alternative embodiment can better capture subtle feature differences in clothing design, improve the accuracy of design element recognition, and is particularly suitable for high-end fashion brands with high requirements for design details.

[0046] Step 3: Obtain environmental data from the standardized dataset, input the feature vectors of clothing design elements and environmental data into the LSTM-based time series prediction model and multi-factor influence model to obtain the fashion trend prediction results; Based on the feature vectors of design elements and environmental data, a time series prediction model based on Long Short-Term Memory (LSTM) is used to obtain the prediction results of future trends.

[0047] Step 3.1: Construct a multi-factor trend influence model; Based on historical trend data in a standardized dataset, a multivariate time series analysis method was used to obtain the weight distribution of trend influencing factors.

[0048] Before building a multi-factor model, data preprocessing of various influencing factors is required to ensure the model's effectiveness: The steps for handling seasonal factors are as follows: collect periodic time feature data such as months and quarters, then convert these time features into sine and cosine encoding forms, and eliminate the influence of linear trends in the time series through trigonometric function transformation to ensure that seasonal changes can be correctly identified and processed by the model.

[0049] The steps for processing economic factors are as follows: collect raw data of various economic indicators such as GDP growth rate, consumer price index, and unemployment rate; calculate the mean and standard deviation of each economic indicator in historical data; then perform Z-score standardization on each data point by subtracting the mean and dividing by the standard deviation to ensure that different economic indicators have the same numerical range and distribution characteristics.

[0050] The steps for processing cultural event factors are as follows: identify and collect information on categorized events such as holidays and cultural activities, convert these categorized events into one-hot encoded vector representations, evaluate the impact intensity of each event, and perform a linear transformation on the impact intensity values ​​through the minimum and maximum values ​​to map them into a standardized range of 0-1.

[0051] The steps for processing social media popularity factors are as follows: collect raw data of social media-related indicators such as search popularity, number of topic mentions, and number of reposts; perform logarithmic transformation on these data to reduce the skewness of the data distribution; then calculate the minimum and maximum values ​​of the transformed data; and map the data to the 0-1 interval using the minimum and maximum normalization methods.

[0052] Through the above systematic preprocessing steps, we can ensure that influence factors of different types and dimensions can be reasonably weighted and effectively represented in the multi-factor model.

[0053] A multi-factor model for trend prediction is established, comprehensively considering seasonal factors, economic factors, cultural event factors, and social media popularity factors. The calculation steps for the trend prediction value are as follows: Factor weight determination: Based on historical data analysis and expert experience, weight coefficients are assigned to seasonal factors, economic factors, cultural event factors, and social media popularity factors to ensure that the sum of the four weight coefficients equals 1.

[0054] Seasonal Factor Calculation: Based on the current time point, calculate the impact of seasonal factors on fashion trends, taking into account the cyclical influence of spring, summer, autumn and winter seasons on clothing fashion trends.

[0055] Economic Factors Calculation: Collect current economic indicator data, including GDP growth rate, consumer price index, unemployment rate, etc., and calculate the impact of the economic environment on consumers' purchasing power and willingness to consume fashion.

[0056] Cultural event factor calculation: Identify important cultural events, holidays, social hotspots, etc. in the current period, assess the driving effect of these events on clothing fashion trends, and calculate the impact value of cultural event factors.

[0057] Social media popularity calculation: Statistics on fashion-related search popularity, topic mentions, and reposts on social media platforms are collected to calculate the impact value of social media popularity factors.

[0058] Weighted summation calculation: Multiply the influence value of each factor by its corresponding weight coefficient, and then sum all the weighted results to obtain the basic prediction value.

[0059] Error term handling: Considering the uncertainty in the prediction process, a random error term is added to the basic predicted value. This error term follows a normal distribution and reflects the random fluctuations in the prediction.

[0060] Final forecast: The base forecast is added to the error term to obtain the final trend forecast index.

[0061] Step 3.2: Establish a time series prediction model based on LSTM; Based on LSTM, a multi-layer recursive structure is used to obtain long-term dependency patterns in time series data. A deep network architecture consisting of an input layer, multiple LSTM hidden layers, and an output layer is constructed, and the model parameters are trained using the backpropagation algorithm. A time window length of 30 days is set to predict the trend changes over the next 7 days.

[0062] Step 3.3: Optimize the accuracy of trend forecasting; Based on error analysis between the predicted results and actual trends, model ensemble techniques are employed to achieve more stable and accurate predictive performance. Multiple predictive models with different architectures, including LSTM, GRU, and Transformer, are combined using a weighted average to fuse their predictions. The mean absolute percentage error (MAPE) metric is used to evaluate predictive accuracy.

[0063] Furthermore, reinforcement learning-optimized prediction models can replace traditional supervised learning methods. Based on the Actor-Critic algorithm framework, an environment-feedback-driven learning strategy is adopted to obtain a predictive model that can adaptively adjust. This alternative embodiment uses market feedback as a reward signal, enabling continuous optimization of the prediction strategy and improving the responsiveness to sudden trends.

[0064] Step 4: Perform user preference clustering analysis on multi-dimensional user characteristics to obtain user preference mining results; Based on user behavior data and consumption records, cluster analysis and deep learning techniques are used to obtain a refined user preference model and personalized profile.

[0065] Step 4.1: Construct a multi-dimensional user feature system; Based on user purchase history, browsing behavior, social media activity, and other data, feature engineering methods are used to obtain user preference mining results.

[0066] Standardization preprocessing for different types of raw data: The steps for processing demographic data are as follows: Categorical variables (such as gender: male / female, geographic location: city name) are converted into one-hot encoded vectors to ensure that each category corresponds to a binary feature dimension; For continuous variables (such as age: 18-65 years old), minimum and maximum normalization are performed through the following steps: Determine the minimum and maximum values ​​of the feature in the dataset, and then for each data point, subtract the minimum value from the original value of the data point, and then divide by the difference between the maximum and minimum values, finally mapping the result to the 0-1 interval.

[0067] The steps for processing user behavior data are as follows: Standardize indicators of different dimensions, including browsing frequency (number of times / day), dwell time (seconds), click behavior (number of times / session), etc. The Z-score standardization method is used for processing: calculate the mean and standard deviation of each indicator in historical data, and then for each data point, subtract the mean from the original value of the data point and divide by the standard deviation to ensure that different behavior indicators have the same numerical range and distribution characteristics.

[0068] The processing steps for preference data are as follows: the user's historical ratings (out of 1 to 5) are normalized to the 0-1 range through a linear transformation. Specifically, the rating is subtracted by 1 and then divided by 4. For missing ratings, the average user rating or the average item rating is used to fill in the missing ratings to ensure data integrity.

[0069] The steps for processing social features are as follows: logarithmic transformation is performed on indicators such as influence index and social activity to eliminate the influence of skewed data distribution, and then the transformed data is mapped to the standardized interval through minimum and maximum normalization methods.

[0070] By statistically analyzing user browsing frequency, dwell time, and click behavior within a time window, and calculating statistical characteristics of the behavioral sequences such as mean, variance, and trend, we can determine user preferences. For preference data, a preference rating matrix is ​​constructed based on users' historical ratings and feedback, and latent preference factors are extracted using matrix factorization techniques. Social features are analyzed by examining users' social network data, including their following relationships, interaction behaviors, and content sharing, to calculate their influence index and social activity. The steps for constructing user feature vectors are as follows: Demographic feature extraction: Collect basic information such as users' age, gender, and geographical location to form demographic feature sub-vectors.

[0071] Behavioral feature calculation: Statistics on user browsing frequency, dwell time, click behavior, and other indicators are collected to calculate the statistical features of the behavioral sequence and form behavioral feature sub-vectors.

[0072] Preference feature construction: Based on users' historical ratings and feedback data, potential preference factors are extracted through matrix factorization techniques to form preference feature sub-vectors.

[0073] Social Feature Analysis: Analyze users' social network data such as follower relationships, interaction behaviors, and content sharing to calculate influence index and social activity, forming social feature sub-vectors.

[0074] Feature vector combination: Connect the demographic feature sub-vectors, behavioral feature sub-vectors, preference feature sub-vectors, and social feature sub-vectors in sequence to form a complete user feature vector.

[0075] Step 4.2: Perform user preference cluster analysis; Based on multi-dimensional user characteristics, the K-means clustering algorithm is used to obtain subcategories of the user group. Users with similar preferences are grouped into the same category by calculating the Euclidean distance between user feature vectors. The optimal number of clusters is optimized using the elbow rule and silhouette coefficient. The user similarity calculation process is as follows: Vector dot product calculation: Calculate the dot product of two user feature vectors, which is to multiply the feature values ​​of corresponding dimensions and then sum them.

[0076] Vector norm calculation: Calculate the Euclidean norm of the two user feature vectors respectively, which is the square root of the sum of the squares of the eigenvalues ​​of each dimension.

[0077] Cosine similarity calculation: Divide the dot product of the vectors by the product of the norms of the two vectors to obtain the cosine similarity value.

[0078] Similarity Interpretation: Cosine similarity ranges from -1 to 1. The closer the value is to 1, the more similar the user preferences are; the closer the value is to -1, the greater the difference in user preferences; and the closer the value is to 0, the less significant the correlation between user preferences.

[0079] Step 4.3: Establish a personalized preference prediction model; Based on user clustering results and historical preference data, a collaborative filtering algorithm is used to predict user preferences for different design elements. A user item rating matrix is ​​constructed, and matrix factorization techniques are used to mine potential user preference factors. A user preference rating prediction model is established to generate personalized design recommendations for each user.

[0080] Furthermore, a user preference modeling method based on graph neural networks can be used to replace the traditional collaborative filtering algorithm. Based on user social relationship graphs and product association graphs, a graph convolutional network is employed to obtain richer user and product representations. This alternative embodiment can fully utilize user social network information and product attribute relationships, improving the accuracy of preference prediction and the diversity of recommendations.

[0081] Step 5: Input the user preference mining results and popular trend prediction results into the generative adversarial network to obtain candidate design schemes. Optimize, evaluate and screen the candidate design schemes to obtain personalized design schemes. Based on the results of trend prediction and user preference mining, generative adversarial networks and multi-objective optimization algorithms are used to obtain personalized design schemes.

[0082] Step 5.1: Construct a generative adversarial network for clothing design; Based on the GAN (Generative Adversarial Network) architecture, an adversarial training mechanism between the generator and discriminator is employed to obtain a model capable of generating innovative design solutions. The generator network takes user preference features and popular trend information as input and outputs candidate design solutions. The discriminator network is responsible for evaluating the quality and realism of the generated designs. Through an iterative optimization process, the generator is able to produce design solutions that are both in line with user preferences and innovative.

[0083] Step 5.2: Implement multi-objective design optimization; Based on the generated candidate design schemes, a multi-objective genetic algorithm is used to obtain the Pareto optimal solution set.

[0084] Before performing multi-objective optimization, the input parameters of each objective function need to be preprocessed to ensure the rationality of the calculation: The preprocessing steps for market adaptability scoring are as follows: It is necessary to normalize indicators of different dimensions, such as trend matching degree (0-1 range), historical sales data (sales volume value), and market capacity (market size value), and use the minimum and maximum normalization methods to unify them into the 0-1 range. Specifically, the minimum and maximum values ​​of each indicator are found, and then the original value is subtracted from the minimum value and divided by the difference between the maximum and minimum values.

[0085] The preprocessing steps for user satisfaction ratings are as follows: the ratings (out of 1 to 5) of different user groups need to be mapped to the 0-1 range through linear transformation, the preference weights (0-1 range) are kept within their original numerical range, the categorical features in the demographic features (a mixture of categorical and numerical features) are converted into one-hot codes, and the numerical features are standardized to ensure that different types of features can be reasonably integrated.

[0086] For the preprocessing steps of innovation scoring: the design similarity (cosine similarity: -1 to 1) needs to be mapped to the 0-1 interval through linear transformation. Specifically, the similarity value is added by 1 and then divided by 2. The novelty index of design elements is processed to the 0-1 interval through the minimum and maximum normalization methods.

[0087] For the preprocessing steps of production costs, it is necessary to standardize the cost components such as raw material costs (currency unit), labor costs (currency unit), and equipment costs (currency unit), and normalize them by using the cost percentage method, that is, dividing each cost component by the total cost, to ensure the numerical stability and comparability of the cost function.

[0088] Establish a multi-objective optimization function that simultaneously considers multiple objectives such as market adaptability, user satisfaction, production cost, and innovation. The steps for performing multi-objective optimization are as follows: Objective function definition: Four optimization objectives are determined, namely, maximizing market adaptability, maximizing user satisfaction, maximizing innovation, and minimizing production costs.

[0089] The calculation of the objective function specifically includes: Market adaptability score calculation: Based on the trend prediction results, the matching degree between the design scheme and the current trend is calculated. Combined with historical sales data analysis of the market performance of similar designs, a comprehensive market adaptability score is calculated by weighted summation. The weight coefficients are determined based on factors such as trend matching degree, historical performance similarity and market capacity. Finally, it is mapped to the 0 to 1 range through the sigmoid function.

[0090] User satisfaction score calculation: Based on the user preference model, the degree of matching between the design scheme and the preferences of the target user group is calculated. The collaborative filtering algorithm is used to predict the user's rating of the design scheme. Personalized adjustments are made in combination with user profile data. The weighted average method is used to calculate the comprehensive satisfaction score of different user groups.

[0091] Innovation score calculation: The similarity between the design scheme and all designs in the historical design library is calculated, and the minimum similarity value is taken as the basic innovation score. Then, it is adjusted by combining factors such as the novelty of design elements and the uniqueness of the combination, and finally the innovation score in the range of 0 to 1 is obtained.

[0092] Production cost calculation: Based on parameters such as fabric selection, process complexity, and production batch size in the design scheme, the cost estimation model is used to calculate the raw material cost, labor cost, and equipment cost, and the total production cost is obtained by linear weighted summation.

[0093] Multi-objective vector construction: Market adaptability score, user satisfaction score, and innovation score are used as maximization objectives, and the negative value of production cost is used as the maximization objective (to minimize cost), thus constructing a multi-objective function vector.

[0094] Pareto optimal solution search: A multi-objective genetic algorithm is used to search for the Pareto optimal solution set through operations such as population initialization, selection, crossover, and mutation, ensuring balanced optimization among the objectives.

[0095] Solution set evaluation and selection: Evaluate the Pareto optimal solution set and select the most suitable design scheme based on the decision-maker's preferences and actual constraints.

[0096] Step 5.3: Perform a quality assessment and screening of the design schemes; Based on the results of multi-objective optimization, the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation were used to obtain a comprehensive score ranking of the design schemes. An evaluation index system for the design schemes was established, including dimensions such as aesthetic score, market potential score, and technical feasibility score. Through a combination of expert review and user surveys, the weight coefficients of each index were determined, and the comprehensive score of the design schemes was calculated.

[0097] Furthermore, reinforcement learning-based design generation methods can be used to replace generative adversarial networks (GANs). Based on the Deep Q-Network (DQN) framework, an interaction mechanism of actions, states, and rewards is employed to obtain a design generation model capable of autonomous learning and improvement. This alternative example, by modeling the design process as a sequential decision problem, allows for better control over the design generation process and results, improving the controllability and quality of the design solutions.

[0098] Step 6: Conduct market forecasting and risk assessment for the personalized design scheme to obtain preliminary market performance assessment results and risk control recommendations; Based on personalized design schemes and market environment data, a market performance prediction model based on random forest is used to obtain the pre-assessment results of the design scheme's market performance and risk control suggestions.

[0099] Step 6.1: Establish a market performance forecasting model; Based on historical product sales data and design features, a random forest regression algorithm is used to predict the sales potential of the design scheme.

[0100] Personalized design feature extraction: The personalized design scheme generated in step 5 is converted into a quantitative design feature vector, including color preference matching degree for a specific user group (0-1 score), style innovation score (based on the degree of differentiation from historical best-selling products), and richness of personalized elements (the number and complexity of personalized elements such as patterns, decorations, and details).

[0101] User group suitability assessment: Based on the user preference model constructed in step 4, calculate the matching degree between the personalized design scheme and the target user group's preferences, and generate a user group suitability feature vector, including dimensions such as age group matching degree, spending power matching degree, and style preference matching degree.

[0102] Personalization Quantification: By comparing the degree of difference between personalized design schemes and mainstream market designs, a personalization index is calculated. This index reflects the uniqueness and differentiation level of the design scheme and serves as an important input feature for the predictive model.

[0103] Before building a predictive model, comprehensive data preprocessing of the input features is required: The preprocessing steps for the design feature vector are as follows: normalize the color features (RGB values: 0-255) to the 0-1 range by dividing by 255; convert the style features (categorical variables) into one-hot encoded vector representations; and perform Z-score standardization on the fabric features (texture complexity, thickness, etc.), that is, calculate the mean and standard deviation, subtract the mean from each value, and then divide by the standard deviation.

[0104] The preprocessing steps for the market environment feature vector are as follows: seasonal factors are encoded as periodic features; sine and cosine transforms are used to convert time information into continuous numerical features; economic indicators (GDP growth rate, consumer confidence index, etc.) are normalized and mapped to the 0-1 interval using minimum and maximum normalization methods; consumer trend data (search popularity, number of mentions on social media, etc.) are processed through logarithmic transformation to reduce data skewness, and then standardized.

[0105] The preprocessing steps for competitor feature vectors are as follows: competitor prices (currency units) are normalized by price range, i.e., the minimum and maximum price ranges are determined, and then the prices are mapped to the 0-1 range. Competitor style features are converted into similarity scores (0-1 range) with the target design. The similarity scores are calculated by comparing features and similarity. The market share (percentage) is directly divided by 100 to convert it into a value in the 0-1 range.

[0106] Through the above systematic preprocessing steps, it is ensured that features of different types and dimensions can be reasonably weighted and effectively recognized in the random forest model.

[0107] Construct a predictive model incorporating multi-dimensional inputs, including design features, market environment, and competitor information. Predictive metrics include expected sales volume, market share, and profitability. The execution steps of the sales volume prediction model are as follows: Feature vector construction: Combine the design feature vector (including design elements such as color, style, and fabric), the market environment feature vector (including factors such as season, economic conditions, and consumption trends), and the competitor feature vector (including information such as competitor prices, styles, and market share) into a complete input feature vector.

[0108] Random Forest Model Construction: Construct multiple decision tree models, each trained on a randomly sampled training subset and feature subset, and combine the prediction results of multiple decision trees using the bootstrap aggregation method.

[0109] Feature Importance Assessment: Feature selection and importance assessment are performed on the input multi-dimensional feature vector to identify the feature variables that have the greatest impact on sales forecasting.

[0110] Decision tree ensemble prediction: The final prediction value is calculated by integrating the prediction results of multiple decision trees. The mean aggregation strategy is used to reduce the prediction error of individual models and the risk of overfitting.

[0111] Forecast output: Outputs the expected sales forecast, along with the forecast confidence interval and uncertainty assessment.

[0112] Step 6.2: Conduct a multi-dimensional risk assessment; Based on the uncertainty analysis of the prediction results, the Monte Carlo simulation method is used to obtain a risk assessment report for the design scheme.

[0113] Personalized risk factor identification: In view of the special characteristics of personalized design solutions, identify risk factors related to the degree of personalization, including market acceptance risk (excessive personalization may lead to niche market), production complexity risk (personalized elements increase production difficulty and cost), and inventory risk (personalized products are more difficult to predict demand).

[0114] User group risk assessment: Based on the characteristics of the target user group of the personalized design plan, assess the risks related to the user group, including the risk of target user group size, the risk of fluctuation in spending power, the risk of changes in preferences, etc., and simulate the impact of changes in different user group parameters on sales performance through Monte Carlo simulation.

[0115] Personalized premium risk analysis: Assess the pricing strategy risk of personalized design solutions, analyze the balance between personalized premium and market acceptance, and determine the optimal pricing range and risk threshold through sensitivity analysis.

[0116] Establish a risk assessment indicator system, including dimensions such as market risk, technological risk, cost risk, and time risk. Through probability distribution simulation and sensitivity analysis, assess the impact of various uncertainties on the probability of project success.

[0117] Step 6.3: Generate decision support reports and recommendations; Based on the pre-assessment results and risk analysis, decision tree analysis is used to obtain decision recommendations for different situations.

[0118] Personalized Solution Optimization Suggestions: Based on the forecast results and risk assessment, specific optimization suggestions are provided for personalized design solutions, including suggestions for adjusting personalized elements (such as reducing overly complex personalized elements to control costs), suggestions for segmenting the target user group (such as adjusting the scope of the target user group to expand the market), and suggestions for balancing the degree of personalization (finding the optimal balance between uniqueness and market acceptance).

[0119] Layered decision-making strategy formulation: For design schemes with different levels of personalization, a layered decision-making strategy is formulated, including a small-batch trial production strategy for highly personalized schemes, a phased promotion strategy for moderately personalized schemes, and a large-scale production strategy for low-personalization schemes, providing managers with differentiated investment and production decision-making suggestions.

[0120] Personalized Value Assessment Report: Generates a value assessment report specifically for personalized design solutions, quantifying the intangible benefits brought by personalization, such as premium potential, brand value enhancement, and increased user loyalty, providing decision-makers with a comprehensive return on investment analysis.

[0121] Establish a decision support system to provide managers with comprehensive reports containing information such as expected returns, risk levels, and investment recommendations. Use visual charts to display key indicators and trends to support rapid decision-making.

[0122] Furthermore, a dynamic risk assessment method based on deep reinforcement learning can be used to replace the traditional statistical model. Based on temporal difference learning, a dynamically adjusted risk assessment strategy is employed to obtain a risk control model that can adapt to changes in the market environment. This alternative example, through continuous learning of market feedback, can adjust risk assessment criteria in real time, improving the accuracy and timeliness of risk warnings.

[0123] In one embodiment of the present invention, in order to compare the accuracy of real-time feedback data of personalized design schemes with the market performance pre-evaluation results, the big data collection and analysis method based on clothing design further includes: A performance monitoring system is established based on real-time feedback data of personalized design schemes. The accuracy of the assessment is evaluated by comparing the real-time feedback data of personalized design schemes with the market performance pre-evaluation results. Online learning and incremental learning technologies are used to update the market performance prediction model. Specifically, it includes the following: Based on the actual market performance and user feedback of personalized design solutions, a continuously optimized big data analysis system is obtained by adopting online learning and model update technologies.

[0124] Based on post-launch sales data, user reviews, and market feedback, data stream processing technology is employed to obtain real-time performance feedback information. A multi-channel feedback collection network is constructed, including data sources such as point-of-sale (POS) systems, customer service centers, and social media monitoring. A standardized processing workflow for feedback data is established to ensure the timeliness and accuracy of feedback information.

[0125] Based on the collected feedback data, a model performance monitoring algorithm is used to obtain the accuracy evaluation results of each prediction model.

[0126] Establish a performance monitoring system based on personalized design schemes: Build a performance monitoring framework specifically for personalized design schemes, including personalized design scheme identification code management, real-time feedback data collection interface, and pre-evaluation result storage module, to ensure that the predicted results of each personalized design scheme can be accurately matched and compared with the actual performance.

[0127] Conduct comparative analysis of market performance pre-assessment results: Use the market performance pre-assessment results generated in step 6 as a benchmark and conduct a systematic comparison with the real-time feedback data of the personalized design scheme. Specifically, this includes deviation analysis between predicted sales and actual sales, correlation analysis between predicted user acceptance and actual user ratings, and consistency verification between predicted market risks and actual market performance.

[0128] Establish a prediction accuracy evaluation index system: Based on the comparison between the pre-evaluation results and the actual feedback data, calculate the prediction accuracy evaluation index, including the mean absolute percentage error (MAPE) of sales forecast, the Pearson correlation coefficient of user acceptance forecast, the accuracy and recall rate of risk warning, and evaluate the reliability of the market performance prediction model through quantitative indicators.

[0129] By comparing real-time feedback data of personalized design solutions with market performance pre-evaluation results, the performance differences of the prediction model under different levels of personalization, different user groups, and different market environments can be identified, providing precise directions for model optimization.

[0130] Based on the performance diagnostic results, an updated and optimized market performance prediction model is obtained using an online learning algorithm.

[0131] Establish a performance monitoring system based on real-time feedback data: Build a real-time data acquisition and processing framework, including modules for user behavior data stream processing, real-time acquisition of market feedback information, and tracking of design scheme effects, to ensure the timeliness and accuracy of feedback data.

[0132] Implement a pre-assessment result comparison and verification mechanism: compare and analyze the real-time feedback data with the market performance pre-assessment results generated in step 6 to evaluate the accuracy and reliability of the prediction model. Quantify the performance of the prediction model by calculating prediction bias, correlation analysis, and trend consistency testing.

[0133] Online and incremental learning are employed to update the prediction models: Based on comparative validation results, algorithms such as online gradient descent, incremental support vector machines, and streaming learning are used to update the fashion trend prediction model, user preference mining model, and market performance prediction model in real time. An adaptive learning rate adjustment mechanism is implemented to ensure that the models can quickly adapt to market changes.

[0134] Establish model version management and rollback mechanisms: Create a version identifier for each model update, record performance metric changes before and after the update, and quickly roll back to a stable version when the new model's performance degrades, ensuring system reliability and stability. Implement an incremental learning strategy to continuously incorporate new data and feedback information without losing historical knowledge. Verify the effectiveness of model updates through A / B testing to ensure continuous improvement in system performance.

[0135] Furthermore, a distributed model optimization method using federated learning can be used to replace centralized online learning. Based on the federated learning framework, a distributed collaborative training strategy is employed to obtain an optimized model that can utilize data from multiple parties while protecting privacy. This alternative example is particularly suitable for application scenarios that require integrating data from multiple partners but have data privacy constraints, enabling collaborative model optimization while protecting data privacy.

[0136] Big data collection and analysis system based on clothing design, such as Figure 2 As shown, the method for performing the above-mentioned big data collection and analysis based on clothing design includes: The data acquisition module is used to acquire multi-source heterogeneous data based on e-commerce platforms and social media; data quality assessment algorithms and cleaning techniques are used to obtain standardized datasets from the multi-source heterogeneous data. The feature extraction module is used to extract feature models of clothing images from standardized datasets using deep learning feature extraction technology; quantify the design elements of clothing image features and analyze the correlation between elements to obtain feature vectors of clothing design elements; The trend prediction module is used to acquire environmental data from a standardized dataset. It uses an LSTM-based time series prediction model and a multi-factor influence model on the feature vectors of clothing design elements and environmental data to obtain the trend prediction results. The user analysis module is used to obtain multi-dimensional user features based on standardized datasets using feature engineering methods; it performs user preference clustering analysis on the multi-dimensional user features, establishes a personalized preference prediction model, and obtains user preference mining results. The design generation module is used to input user preference mining results and popular trend prediction results into the generative adversarial network to obtain candidate design schemes, optimize the candidate design schemes, evaluate their quality and screen them to obtain personalized design schemes; The market assessment module is used to predict the market performance of personalized design solutions using a random forest-based market performance prediction model; the prediction results are then used to conduct a risk assessment using the Monte Carlo simulation method to obtain the pre-assessment results of market performance and risk control recommendations. The update and optimization module is used to establish a performance monitoring system based on real-time feedback data of personalized design schemes, compare the real-time feedback data of personalized design schemes with the market performance pre-evaluation results to assess accuracy, and use online learning and incremental learning technologies to update the market performance prediction model.

[0137] In one embodiment of the present invention, a specific example is provided: A 30-day field test was conducted in District B of City A. During the test, a distributed data collection system was deployed, covering 15 major business districts and shopping centers within the area, spanning approximately 50 square kilometers. By setting up intelligent data collection terminals within shopping malls and combining them with a mobile user behavior tracking system, consumer shopping behavior data and preference information were collected in real time. The test system processed over 100,000 data entries daily, covering the entire user behavior process, including browsing, trying on clothes, and purchasing.

[0138] Table 1 shows an example of data collection from e-commerce platforms: Table 1: Examples of data collection from e-commerce platforms;

[0139] Table 2 shows an example of social media trend data collection: Table 2: Examples of Social Media Trend Data Collection;

[0140] like Figure 3As shown, the performance of the method of this invention in various trend prediction tasks is demonstrated. Compared with traditional prediction methods, this invention achieves accuracy improvements of 22%, 26%, 27%, 27%, and 25% in color trend, style trend, fabric trend, pattern trend, and overall trend prediction, respectively. Particularly in fabric trend prediction, the accuracy reaches 89%, superior to the 62% of traditional methods, demonstrating the advantages of multi-dimensional data fusion and deep learning technology.

[0141] like Figure 4 As shown, the improvement in user satisfaction before and after applying the system of this invention is demonstrated. In terms of design innovation, satisfaction increased from 3.2 to 4.3, an increase of 34%; personalization increased from 2.8 to 4.1, an increase of 46%; and popularity compatibility increased from 3.1 to 4.5, an increase of 45%. Overall satisfaction improved from 3.1 to 4.3, indicating that users showed higher approval of the design solution based on big data analysis.

[0142] like Figure 5 As shown, the present invention demonstrates its effectiveness in improving various business metrics. Sales conversion rate increased from 72% to 95%, new product success rate increased from 58% to 85%, inventory turnover rate increased from 65% to 88%, design efficiency increased from 45% to 78%, and market responsiveness increased from 52% to 90%. These improvements validate the commercial value and practicality of the clothing design method based on big data collection and analysis. Through accurate trend prediction and personalized recommendations, the system effectively reduces market risk and improves resource utilization efficiency.

[0143] The embodiments of the present invention have been described above. However, the embodiments are not limited to the specific implementation methods described above. The specific implementation methods described above are merely illustrative and not restrictive. Those skilled in the art can make more equivalent embodiments under the guidance of the present embodiments, and all of them are within the protection scope of the present embodiments.

Claims

1. A big data collection and analysis method based on clothing design, characterized in that, include: Acquire multi-source heterogeneous data, including sales data from e-commerce platforms, user-generated content from social media, professional information from fashion websites, and environmental data. Apply data quality assessment algorithms and cleaning techniques to the multi-source heterogeneous data to obtain a standardized dataset. Use feature engineering to extract clothing image features and multi-dimensional user features from the standardized dataset. Quantify the design elements of the clothing image features and analyze the correlation between these elements to obtain clothing design element feature vectors. Acquire environmental data from the standardized dataset, and input the clothing design element feature vectors and environmental data into an LSTM-based time series prediction model and a multi-factor influence model to obtain fashion trend prediction results. User preference clustering analysis is performed on multi-dimensional user characteristics to obtain user preference mining results; The user preference mining results and popular trend prediction results are input into the generative adversarial network to obtain candidate design solutions. The candidate design solutions are then optimized, their quality is evaluated, and they are screened to obtain personalized design solutions. Market forecasting and risk assessment are conducted on personalized design solutions to obtain preliminary market performance assessment results and risk control recommendations.

2. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The process of acquiring multi-source heterogeneous data specifically includes: constructing a distributed crawler cluster to monitor the e-commerce platform in real time, using web crawler technology to acquire product descriptions, prices, sales volume, and user reviews to obtain e-commerce platform data; based on the acquired e-commerce platform data, using keyword matching and topic tracking technology through social media API calls to acquire fashion user-generated content to obtain social media data; and integrating the e-commerce platform data and social media data with professional information from fashion websites to obtain multi-source heterogeneous data.

3. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The data quality assessment algorithm and cleaning technology specifically include: acquiring multi-source heterogeneous data; detecting the encoding format of text data in the multi-source heterogeneous data; uniformly converting the detected different encoding formats into UTF-8 encoding; performing format verification and size normalization processing on image data in the multi-source heterogeneous data; detecting outliers in the processed multi-source heterogeneous data based on rules and statistical methods; marking and removing detected price anomalies, rating anomalies, and timestamp anomalies to obtain a standardized dataset.

4. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The specific process of generating the feature vector of the clothing design elements includes: obtaining a standardized dataset; using deep learning feature extraction technology to construct a clothing image feature extraction model for the standardized dataset; extracting basic visual features from clothing images through a pre-trained ResNet network; constructing a clothing attribute recognition branch network based on the basic visual features to identify design elements; establishing a color feature vector; defining a style innovation index by calculating the similarity difference between the design style and historical popular styles; and obtaining the feature vector of the clothing design elements.

5. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The steps for generating the trend prediction results specifically include: acquiring feature vectors of clothing design elements and environmental data; establishing a multi-factor influence model based on the feature vectors of clothing design elements and environmental data, comprehensively considering seasonal factors, economic factors, cultural event factors, and social media popularity factors; training the multi-factor influence model using an LSTM-based time series prediction model, setting the time window length and prediction time length; and fusing the prediction results of each model by combining prediction models with different architectures using a weighted average method to obtain the trend prediction results.

6. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The process of generating the user preference mining results specifically includes: obtaining the trend prediction results; constructing a user behavior dataset based on the trend prediction results, which includes user browsing history, purchase history, evaluation history, and collection history; analyzing the user behavior dataset using a collaborative filtering algorithm to calculate the user similarity matrix and the item similarity matrix; constructing a user preference model based on the user similarity matrix and the item similarity matrix; and dividing users into different preference groups using a clustering algorithm to obtain the user preference mining results.

7. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The generation of the personalized design scheme specifically includes: obtaining user preference mining results; constructing design constraints based on the user preference mining results, including cost constraints, material constraints, and process constraints; optimizing and solving the design constraints using a genetic algorithm, setting the population size, crossover probability, and mutation probability; evaluating the market adaptability and user satisfaction of the design scheme through a fitness function; and selecting the final design scheme through multiple generations of evolution to obtain the personalized design scheme.

8. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, The process of generating the market performance pre-assessment results and risk control recommendations specifically includes: obtaining a personalized design scheme; constructing a market performance prediction model based on a random forest based on the personalized design scheme; the market performance prediction model includes sales forecast, user acceptance forecast, and market risk assessment; conducting a multi-dimensional risk assessment of the market performance prediction model using the Monte Carlo simulation method, setting the number of simulations and confidence intervals; generating a decision support analysis report based on the multi-dimensional risk assessment results, and obtaining the market performance pre-assessment results and risk control recommendations.

9. The big data collection and analysis method based on clothing design according to claim 1, characterized in that, Also includes: A performance monitoring system is established based on real-time feedback data of personalized design schemes. The accuracy of the assessment is evaluated by comparing the real-time feedback data of personalized design schemes with the market performance pre-evaluation results. Online learning and incremental learning technologies are used to update the market performance prediction model.

10. A big data collection and analysis system based on clothing design, characterized in that: The method for performing big data collection and analysis based on clothing design as described in any one of claims 1-9 comprises: a data collection module for acquiring multi-source heterogeneous data, including e-commerce platform sales data, social media user-generated content, fashion website professional information, and environmental data; applying data quality assessment algorithms and cleaning techniques to the multi-source heterogeneous data to obtain a standardized dataset; a feature extraction module for extracting clothing image features and multi-dimensional user features from the standardized dataset using feature engineering; quantifying the design elements of the clothing image features and analyzing the correlation between elements to obtain a clothing design element feature vector; and a trend prediction module for acquiring environmental data from the standardized dataset, and inputting the clothing design element feature vector and environmental data into an LSTM-based time series prediction model and a multi-factor influence model. The system comprises four modules: a response model to predict trends; a user analysis module to perform user preference clustering analysis on multi-dimensional user characteristics to obtain user preference mining results; a design generation module to input user preference mining results and trend prediction results into a generative adversarial network to obtain candidate design schemes, optimize, evaluate, and screen these schemes to obtain personalized design schemes; a market evaluation module to perform market forecasting and risk assessment on personalized design schemes to obtain market performance pre-evaluation results and risk control suggestions; and an update and optimization module to establish a performance monitoring system based on real-time feedback data of personalized design schemes, compare the accuracy of real-time feedback data of personalized design schemes with market performance pre-evaluation results, and update the market performance prediction model using online learning and incremental learning techniques.

Images