Plastic product research and development data processing method and system

Abstract

The invention discloses a plastic product research and development data processing method and system, and particularly relates to the technical field of plastic products. The extracted material performance complexity features and market feedback real-time features are comprehensively analyzed through fuzzy logic, so that the reliability of a product prediction model is accurately evaluated, according to the prediction result of the model, the result is further divided into an accuracy prediction result, a possible accuracy prediction result and an inaccuracy prediction result, and the prediction accuracy of the product is further improved. And corresponding treatment measures are taken according to different categories, so that the research and development efficiency is improved, the market adaptability and quality of products are ensured, enterprises can better meet the market requirements, and the overall competitiveness is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of plastic products, and in particular to a data processing method and system for plastic product research and development. Background Art

[0002] Data processing for plastic product R&D refers to the collection, organization and analysis of data related to material properties, processing technology, product design, etc. during the R&D process of plastic products. These data can include experimental results, market research, user feedback, and monitoring data during the production process. Through data processing, the R&D team can identify potential areas for improvement, optimize material formulations and production processes, and improve product performance and market competitiveness.

[0003] In the process of data processing, techniques such as statistical analysis, data visualization, and machine learning are usually used. These techniques can help R&D personnel extract valuable information from complex data sets, predict the performance of products in actual use, and quickly verify design assumptions. Ultimately, through effective data processing, companies can more efficiently develop plastic products that meet market demand, thereby improving overall R&D efficiency and product quality. However, when building a predictive model, if too much attention is paid to the details in the training data, the model may capture noise rather than real patterns. Although the model performs well on the training data, in actual applications, the prediction results may be inaccurate, causing the R&D team to incorrectly evaluate the reliability and performance of the product. Summary of the invention

[0004] The purpose of the present invention is to provide a data processing method and system for plastic product research and development to solve the shortcomings of the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for processing data for plastic product research and development, comprising the following steps: S1: collecting plastic product R&D data from different data sources, wherein the plastic product R&D data includes material performance data and market feedback data, and preprocessing the acquired plastic product R&D data; S2: Extract features from the pre-processed plastic product R&D data, and extract the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; S3: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; S4: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

[0006] Preferably, in S2, a material performance complexity index is generated according to the material performance complexity characteristics in the extracted material performance data, and the method for obtaining the material performance complexity index is: Obtain the performance data of all materials, construct a data set, standardize the data, and calculate the covariance matrix of the standardized data. The expression is: ; Where C is the covariance matrix, X′ is the standardized data matrix, n is the number of samples, T is the matrix transpose, and the eigenvalues ​​and eigenvectors of the covariance matrix are calculated to identify the principal components: ; λ is the eigenvalue, I is the unit matrix, the principal component is selected according to the size of the eigenvalue, the eigenvalue with a cumulative variance ratio of 85%-95% is selected as the principal component, the standardized data is projected onto the selected principal component, the coordinate Z of each sample in the principal component space is obtained, and the material performance complexity index is calculated by the selected principal component score, and the expression is: ; Where p is the number of principal components selected, is the eigenvalue of the kth principal component, MP material performance complexity index.

[0007] Preferably, in S2, a feedback frequency fluctuation index is generated according to the real-time characteristics of market feedback in the extracted market feedback data, and the method for obtaining the feedback frequency fluctuation index is: Get the market feedback data within the H time period, select the time window W, count the number of feedbacks within this time window, count the number of feedbacks received for each time unit, and generate a feedback frequency sequence: ; Calculate the mean of the feedback frequency in the W time window, the expression is: ; In the formula, MF is the mean value of the feedback frequency. The fluctuation value of the feedback frequency is calculated as follows: ; In the formula, is the fluctuation value of the feedback frequency. The feedback frequency fluctuation index is obtained by performing weighted average summation calculation on the fluctuation values ​​of the feedback frequency in each time window.

[0008] Preferably, in S3, based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by using fuzzy logic for comprehensive analysis, specifically: The material performance complexity index MP and the feedback frequency fluctuation index KL are used as the input items of fuzzy logic, and the accuracy level F of the product prediction model is used as the output item of fuzzy logic; For the material property complexity index, feedback frequency fluctuation index and the accuracy level of the product prediction model, they are divided into fuzzy sets; According to the relationship between input variables, fuzzy rules are formulated to determine the value of output variables; Convert the actual material performance complexity index and feedback frequency fluctuation index into fuzzy values; Evaluate the fuzzy input according to the fuzzy rules, aggregate the output fuzzy sets of all rules, and usually use the maximum aggregation method to form the output fuzzy set; The fuzzy output values ​​are converted into crisp output values, and the final result is the accuracy level of the product prediction model.

[0009] Preferably, in S4, for the possible accuracy prediction results, the product is dynamically adjusted according to the changes in the model prediction accuracy, specifically: Calculate the abnormal degree value of the model prediction accuracy, the expression is: : In the formula, TP is a true positive example, TN is a true negative example, FP is a false positive example, FN is a false negative example, and A is the abnormality value; the adjustment coefficient is calculated as follows: ; In the formula, AF is the adjustment coefficient, K is a constant, Adjusted material properties for target prediction accuracy for: ; M is the current material property, The adjustment range indicates the amount of each adjustment.

[0010] The present invention also provides a data processing system for plastic product research and development, a data acquisition module, a feature extraction module, an accuracy analysis module and a processing module; Data acquisition module: collects plastic product R&D data from different data sources, including material performance data and market feedback data, and pre-processes the acquired plastic product R&D data; Feature extraction module: extracts features from the pre-processed plastic product R&D data, and extracts the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; Accuracy analysis module: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; Processing module: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

[0011] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention can effectively extract valuable information from complex data sets by making full use of statistical analysis, data visualization, and machine learning techniques. This process includes comprehensive collection and preprocessing of material performance data and market feedback data, feature extraction, fuzzy logic analysis, and classification processing of prediction results, thereby significantly improving product R&D efficiency and market adaptability. By generating a material performance complexity index and a feedback frequency fluctuation index, the R&D team can more accurately evaluate product performance and make necessary dynamic adjustments, ensuring that decisions during the R&D process are based on reliable data analysis.

[0012] 2. The present invention uses a data acquisition module, a feature extraction module, an accuracy analysis module and a processing module, and each module cooperates with each other to form an efficient workflow. Such a design not only improves the automation and intelligence level of data processing, but also provides enterprises with the ability to flexibly respond to market changes. Through accurate model prediction, enterprises can quickly respond to market demand, reduce R&D risks, and ultimately promote the quality and performance of plastic products, thereby enhancing market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0014] Figure 1 The present invention is a method flow chart of a data processing method for plastic product research and development.

[0015] Figure 2 The module diagram of a data processing system for plastic product research and development according to the present invention is shown in FIG. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1, please refer to Figure 1 , 2 As shown, a method for processing data for plastic product research and development described in this embodiment includes the following steps: S1: collecting plastic product R&D data from different data sources, wherein the plastic product R&D data includes material performance data and market feedback data, and preprocessing the acquired plastic product R&D data; S2: Extract features from the pre-processed plastic product R&D data, and extract the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; S3: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; S4: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

[0018] Among them, in S1, the plastic product R&D data from different data sources are collected, the plastic product R&D data includes material performance data and market feedback data, and the obtained plastic product R&D data is preprocessed, specifically: Collect plastic product R&D data from different data sources, including material performance data and market feedback data, where material performance data can be collected through laboratory testing, literature review, industry standards, databases, etc. The data usually includes the material's physical properties (such as density, strength, ductility, etc.), chemical properties (such as corrosion resistance, thermal stability, etc.), processing properties (such as melt index, molding temperature, etc.), etc.

[0019] Market feedback data can be obtained through user surveys, customer reviews, market research reports, social media analysis, etc. The data usually includes consumers' satisfaction with plastic products, usage experience, functional evaluation, purchase intention, price sensitivity, etc.

[0020] After collecting material performance data and market feedback data, the following pre-processing steps are required:

[0021] Check if there are missing values ​​in the data set and take appropriate measures to deal with them. You can choose to delete records with missing values, fill missing values ​​with the mean / median, or use interpolation to estimate. Identify and remove outliers in the data to ensure the overall quality of the data set. For example, detect outliers through box plots or Z-score methods. For features of different units in material performance data, standardization or normalization is required so that different features can be compared on the same scale. Market feedback data may contain categorical data (such as user satisfaction ratings), which needs to be encoded (such as one-hot encoding) for subsequent analysis.

[0022] Identify and select features relevant to the R&D goals. You can use methods such as correlation analysis and principal component analysis (PCA) to extract important features and reduce data dimensions. Combine different features to generate new features, such as combining the physical properties of materials with user reviews from market feedback to create a comprehensive scoring feature. Integrate material performance data and market feedback data to form a unified data set. You can connect based on key fields such as product model and batch. Ensure that the integrated data set is consistent in format, structure, and units to facilitate subsequent analysis and modeling.

[0023] Analyze the preprocessed data using data visualization tools such as scatter plots, heat maps, histograms, etc. to identify potential trends, patterns, and relationships. At the final stage of preprocessing, check the integrity and consistency of the data to ensure that the data is reliable in subsequent analysis and modeling.

[0024] S2: Perform feature extraction on the pre-processed plastic product R&D data, and extract the material performance complexity features in the material performance data and the market feedback real-time features in the market feedback data.

[0025] Before feature extraction, you first need to deeply understand the structure, type and information contained in the data. The main data sources include: Material performance data: such as strength, toughness, thermal stability, density, etc. Market feedback data: such as customer ratings, user reviews, sales data, market trends, etc.

[0026] Extraction of basic performance indicators: Extract the basic physical and chemical properties of each material (such as tensile strength, elastic modulus, melt index, etc.) as basic characteristics.

[0027] Composite performance features: Composite features: Combine multiple basic performance indicators to generate composite features. For example, create a "strength / density ratio" feature to evaluate the performance efficiency of a material. Statistical features of performance indicators: Calculate the mean, standard deviation, minimum, maximum, etc. of the performance indicators to form statistical features.

[0028] Complexity features: Diversity index: Evaluate the diversity of material properties by calculating the variance or standard deviation of multiple performance indicators. Feature interaction: Capture the relationship between different performance indicators by creating interactive features (such as the product of strength and ductility). Dimensionality reduction and principal component analysis (PCA): Use PCA to reduce the dimensionality of high-dimensional performance data and extract the main components to reduce redundancy while retaining most of the information.

[0029] Perform sentiment analysis on user reviews and extract the ratio of positive and negative feedback and the comprehensive sentiment score as features. Calculate the timestamp of feedback and extract the response time (such as the number of days from product launch to first feedback) as a feature. Count the number of feedbacks in a specific time period to assess product popularity. Count user ratings (such as star ratings) and extract features such as mean, distribution, and extreme values.

[0030] The material performance complexity index is generated according to the material performance complexity characteristics in the extracted material performance data. The method for obtaining the material performance complexity index is: Obtain the performance data of all materials and construct a data set. The data set should contain multiple features, such as tensile strength, elastic modulus, and ductility. Before performing PCA, the data must first be standardized to eliminate the influence of different feature magnitudes. Calculate the covariance matrix of the standardized data, expressed as: ; Where C is the covariance matrix, X′ is the standardized data matrix, n is the number of samples, T is the matrix transpose, and the eigenvalues ​​and eigenvectors of the covariance matrix are calculated to identify the principal components: ; λ is the eigenvalue, I is the unit matrix, the principal component is selected according to the size of the eigenvalue, the eigenvalue with a cumulative variance ratio of 85%-95% is selected as the principal component, the standardized data is projected onto the selected principal component, the coordinate Z of each sample in the principal component space is obtained, and the material performance complexity index is calculated by the selected principal component score, and the expression is: ; Where p is the number of principal components selected, is the eigenvalue of the kth principal component, MP material performance complexity index.

[0031] The larger the material performance complexity index, the higher the diversity and complexity of the material in multiple performance characteristics, which provides a richer information basis for the product prediction model. When the performance characteristics of the material are more complex and diverse, the model can better learn the potential patterns of material performance under different conditions, thereby improving its predictive ability. A higher material performance complexity index means that the material exhibits greater adaptability when facing different environments and application scenarios, which provides more comprehensive training data for the model.

[0032] Secondly, materials with a higher complexity index often involve multiple interactive performance indicators, such as strength, toughness, and heat resistance, which enables the model to identify the complex relationships between these characteristics when it is built. This complex relationship can help the model capture the key performance of the material in actual use, thereby improving the accuracy of the prediction. By mining these potential interactions, the model can more effectively deal with nonlinear and multidimensional data and reduce the risk of overfitting.

[0033] Finally, when the material performance complexity index increases, the prediction model may also show higher reliability during the verification process. High-complexity material data provides a wider range of test samples for model evaluation, allowing the R&D team to make more accurate performance predictions in actual applications. This can not only improve the accuracy of product design, but also provide guidance for subsequent material optimization, thereby ultimately improving the market competitiveness and user satisfaction of the product.

[0034] The feedback frequency fluctuation index is generated according to the real-time characteristics of market feedback in the extracted market feedback data. The method for obtaining the feedback frequency fluctuation index is: Get market feedback data within a time period of H, including the number of feedbacks received each day or week. This data can come from user reviews, product ratings, or other market surveys. Select an appropriate time window W (such as 7 days, 30 days, or a specific sales cycle) to calculate the feedback frequency. In this time window, count the number of feedbacks received each day or week. Count the number of feedbacks received for each time unit (such as daily or weekly) to generate a feedback frequency sequence: ; Calculate the mean of the feedback frequency in the W time window, the expression is: ; In the formula, MF is the mean value of the feedback frequency. The fluctuation value of the feedback frequency is calculated as follows: ; In the formula, is the fluctuation value of the feedback frequency. The feedback frequency fluctuation index is obtained by performing weighted average summation calculation on the fluctuation values ​​of the feedback frequency in each time window.

[0035] The larger the feedback frequency volatility index, the more volatile the feedback volume is, which may reflect the instability of the product's acceptance and attention in the market. When the feedback frequency is more volatile, the model may face more challenges, because unstable feedback data will make it difficult for the model to capture consistent trends and patterns during the learning phase. In this way, the model may produce greater errors when making future predictions, reducing the accuracy of the predictions.

[0036] Secondly, highly volatile feedback may mean that market demand is changing rapidly, and consumers’ evaluation of products is affected by many factors, such as seasonal changes, promotional activities, or competitors’ market strategies. Such external influences can cause drastic fluctuations in feedback data, making it difficult for the forecasting model to effectively adapt to these changes. As a result, the model may not be able to accurately assess the performance of the product under different market conditions, which in turn affects R&D and market decisions.

[0037] Finally, an increase in the feedback frequency fluctuation index may also indicate that there are large user disagreements and inconsistencies in the product. If negative feedback and positive feedback coexist and change frequently, it will be difficult for the model to determine the true market performance of the product. Such uncertainty reduces the reliability of the model in evaluating the success of the product, which may ultimately lead to wrong business decisions. Therefore, an increase in the feedback frequency fluctuation index usually means that the accuracy of the product prediction model has decreased, and further measures need to be taken to improve data quality and model adaptability.

[0038] S3: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined after comprehensive analysis using fuzzy logic.

[0039] The material performance complexity index MP and the feedback frequency fluctuation index KL are used as the input items of fuzzy logic, and the accuracy level F of the product prediction model is used as the output item of fuzzy logic; The material performance complexity index (MP) is divided into fuzzy sets, such as: low, medium, and high. The feedback frequency fluctuation index (KL) is divided into fuzzy sets, such as: low variation, medium variation, and high variation.

[0040] The accuracy level (F) of the product prediction model divides it into fuzzy sets, such as: inaccurate, moderate, and accurate.

[0041] According to the relationship between the input variables, fuzzy rules are formulated to determine the value of the output variable. For example, the following fuzzy rules can be used: If MP is low, and KL is low volatility, then F is accurate. If MP is low, and KL is medium volatility, then F is probably accurate. If MP is low, and KL is high volatility, then F is inaccurate. If MP is medium, and KL is low volatility, then F is accurate. If MP is medium, and KL is medium volatility, then F is probably accurate. If MP is medium, and KL is high volatility, then F is inaccurate. If MP is high, and KL is low volatility, then F is probably accurate. If MP is high, and KL is medium volatility, then F is inaccurate. If MP is high, and KL is high volatility, then F is inaccurate.

[0042] Convert the actual material performance complexity index (MP) and feedback frequency fluctuation index (KL) into fuzzy values. Membership functions can be used to achieve fuzzification. For example: For MP, the following membership function can be defined: Low: ;middle: ;high: ; The fuzzy input is evaluated according to the fuzzy rules. The input value is combined with the fuzzy rules using the "Max-Min" method (Max-Min) to determine the degree of activation of each rule.

[0043] Aggregate the output fuzzy sets of all rules, usually using the maximum aggregation method (MaxAggregation) to form the output fuzzy set. You can get the activation value of each output category (inaccurate, possibly accurate, accurate).

[0044] Convert fuzzy output values ​​into clear output values ​​(Defuzzification). Commonly used defuzzification methods include the Centroid Method.

[0045] The final result is the accuracy level (F) of the product prediction model, which can be used to support product development and market decisions.

[0046] For example: Material performance complexity index (MP) = 70, feedback frequency fluctuation index (KL) = 20; Fuzzy input data: Calculate the membership of MP and KL through the set membership function. For example: MP = 70 > high (0.8), medium (0.2), low (0) KL = 20 > low fluctuation (0.9), medium fluctuation (0.1), high fluctuation (0); For example, rule 1 is activated: If MP is low and KL is low volatility, then F is accurate. The activation level of this rule is 0. Rule 5 is activated: If MP is medium and KL is low volatility, then F is probably accurate. The activation level of this rule is 0.2* 0.9 = 0.18. Rule 8 is activated: If MP is high and KL is medium volatility, then F is inaccurate. The activation level of this rule is 0.8 * 0.1 = 0.08.

[0047] Summarizing the membership of each output class, we get probably accurate (0.18) and inaccurate (0.08).

[0048] Calculate the output center of gravity value and get the final output result.

[0049] Assuming that the final defuzzification result is “likely accurate”, the accuracy level of the model is likely accurate, which means that the performance of the prediction model is acceptable, but there is still room for improvement.

[0050] S4: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

[0051] According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed, specifically: For accuracy prediction results, such prediction results show that the model's predictions are very close to the actual market performance, and the product performance and market feedback are relatively ideal. For the prediction results marked as accurate, it is recommended to give priority to use in production and marketing. Such products can be marketed more widely to take advantage of their advantages. These accuracy prediction results are analyzed in depth to identify their success factors, such as material selection, design features, market positioning, etc., to form best practices and provide reference for future product development. Although these results show that the model is accurate, market feedback still needs to be continuously monitored to ensure that the product maintains performance under different market conditions.

[0052] For inaccurate prediction results, such prediction results indicate that there is a significant difference between the model's prediction and the actual market performance, and the product may have quality problems or be unacceptable to the market. Conduct in-depth analysis of these results to identify the causes of inaccurate predictions. It may be necessary to trace back to data collection, model design, or parameter setting to troubleshoot the problem. Re-evaluate products identified as inaccurate, including material properties, design characteristics, and market feedback. Decide whether product improvements or redesigns are needed based on the analysis results. If, after detailed analysis, it is confirmed that the product has serious quality problems or is unacceptable to the market, consider temporarily stopping production and making comprehensive improvements. Establish a complete feedback mechanism to feed back inaccurate prediction results to the R&D team, prompting the team to conduct in-depth discussions on the problems and formulate solutions.

[0053] For possible accuracy prediction results, this type of prediction result indicates that there is a certain degree of uncertainty between the model prediction and the actual performance. According to the changes in the model prediction accuracy, the product is dynamically adjusted to flexibly respond to potential problems.

[0054] Calculate the abnormal degree value of the model prediction accuracy, the expression is: : In the formula, TP is a true positive example (correct prediction is accurate), TN is a true negative example (correct prediction is inaccurate), FP is a false positive example (incorrect prediction is accurate), FN is a false negative example (incorrect prediction is inaccurate), and A is the abnormality value; the adjustment coefficient is calculated as follows: ; In the formula, AF is the adjustment coefficient, K is a constant, which indicates the flexibility or sensitivity of the adjustment. Adjusted material properties for target prediction accuracy for: ; M is the current material properties (such as strength, elasticity, etc.), The adjustment range indicates the amount of each adjustment.

[0055] In this embodiment, during the research and development of plastic products, the research and development data from different data sources are first comprehensively collected, including material performance data and market feedback data, and these data are preprocessed to ensure the quality and consistency of the data. Then, through feature extraction technology, the material performance complexity features are extracted from the material performance data, and the market feedback real-time features are extracted from the market feedback data. Based on these extracted features, fuzzy logic is used to conduct a comprehensive analysis of the data to determine the accuracy of the product prediction model. Finally, according to the prediction results of the model, it is divided into accuracy prediction results, possible accuracy prediction results and inaccuracy prediction results, and corresponding processing measures are taken according to different categories to optimize product performance and market performance.

[0056] Embodiment 2, a data processing system for plastic product research and development described in this embodiment includes a data acquisition module, a feature extraction module, an accuracy analysis module and a processing module; Data acquisition module: collects plastic product R&D data from different data sources, including material performance data and market feedback data, and pre-processes the acquired plastic product R&D data; Feature extraction module: extracts features from the pre-processed plastic product R&D data, and extracts the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; Accuracy analysis module: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; Processing module: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0059] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0060] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for processing data for plastic product research and development, characterized in that: The steps include: S1: collecting plastic product R&D data from different data sources, wherein the plastic product R&D data includes material performance data and market feedback data, and preprocessing the acquired plastic product R&D data; S2: Extract features from the pre-processed plastic product R&D data, and extract the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; S3: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; S4: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

2. A method for processing data for plastic product research and development according to claim 1, characterized in that: In S2, a material performance complexity index is generated according to the material performance complexity characteristics in the extracted material performance data, and the method for obtaining the material performance complexity index is: Obtain the performance data of all materials, construct a data set, standardize the data, and calculate the covariance matrix of the standardized data. The expression is: ; Where C is the covariance matrix, X′ is the standardized data matrix, n is the number of samples, T is the matrix transpose, and the eigenvalues ​​and eigenvectors of the covariance matrix are calculated to identify the principal components: ; λ is the eigenvalue, I is the unit matrix, and the principal component is selected according to the size of the eigenvalue. The eigenvalue with a cumulative variance ratio of 85%-95% is selected as the principal component. The standardized data is projected onto the selected principal component to obtain the coordinate Z of each sample in the principal component space. The material performance complexity index is calculated by the selected principal component score, and the expression is: ; Where p is the number of principal components selected, is the eigenvalue of the kth principal component, MP material performance complexity index.

3. A method for processing data for plastic product R&D according to claim 2, characterized in that: In S2, the feedback frequency fluctuation index is generated according to the real-time characteristics of the market feedback in the extracted market feedback data. The method for obtaining the feedback frequency fluctuation index is: Get the market feedback data within the H time period, select the time window W, count the number of feedbacks within this time window, count the number of feedbacks received for each time unit, and generate a feedback frequency sequence: ; Calculate the mean of the feedback frequency in the W time window, the expression is: ; In the formula, MF is the mean value of the feedback frequency. The fluctuation value of the feedback frequency is calculated as follows: ; In the formula, is the fluctuation value of the feedback frequency. The feedback frequency fluctuation index is obtained by performing weighted average summation calculation on the fluctuation values ​​of the feedback frequency in each time window.

4. A method for processing data for plastic product research and development according to claim 3, characterized in that: In S3, based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by using fuzzy logic for comprehensive analysis, specifically: The material performance complexity index MP and the feedback frequency fluctuation index KL are used as the input items of fuzzy logic, and the accuracy level F of the product prediction model is used as the output item of fuzzy logic; For the material property complexity index, feedback frequency fluctuation index and the accuracy level of the product prediction model, they are divided into fuzzy sets; According to the relationship between input variables, fuzzy rules are formulated to determine the value of output variables; Convert the actual material performance complexity index and feedback frequency fluctuation index into fuzzy values; Evaluate the fuzzy input according to the fuzzy rules, aggregate the output fuzzy sets of all rules, and usually use the maximum aggregation method to form the output fuzzy set; The fuzzy output values ​​are converted into crisp output values, and the final result is the accuracy level of the product prediction model.

5. A method for processing data for plastic product R&D according to claim 4, characterized in that: In S4, for the possible accuracy prediction results, the product is dynamically adjusted according to the changes in the model prediction accuracy, specifically: Calculate the abnormal degree value of the model prediction accuracy, the expression is: : In the formula, TP is a true positive example, TN is a true negative example, FP is a false positive example, FN is a false negative example, and A is the abnormality value; the adjustment coefficient is calculated as follows: ; In the formula, AF is the adjustment coefficient, K is a constant, Adjusted material properties for target prediction accuracy for: ; M is the current material property, It is the adjustment range, indicating the amount of each adjustment.

6. A data processing system for plastic product research and development, used to implement a data processing method for plastic product research and development as claimed in any one of claims 1 to 5, characterized in that: Data acquisition module, feature extraction module, accuracy analysis module and processing module; Data acquisition module: collects plastic product R&D data from different data sources, including material performance data and market feedback data, and pre-processes the acquired plastic product R&D data; Feature extraction module: extracts features from the pre-processed plastic product R&D data, and extracts the material performance complexity features from the material performance data and the market feedback real-time features from the market feedback data; Accuracy analysis module: Based on the extracted material performance complexity characteristics and market feedback real-time characteristics, the accuracy of the product prediction model is determined by comprehensive analysis using fuzzy logic; Processing module: According to the prediction results, the prediction results of the product prediction model are divided into accurate prediction results, possible accurate prediction results and inaccurate prediction results, and corresponding processing is performed.

Images