A product design assistance system and method based on big data

Abstract

This invention belongs to the field of intelligent product design technology, specifically relating to a product design assistance system and method based on big data. The method collects data from the entire product design, market, production, and after-sales process, and extracts dynamic trends through time-series analysis. During the solution optimization stage, it verifies material availability, process adaptability, and cost controllability based on production-side data, and corrects design parameters through an after-sales data feedback mechanism. An improved Pareto optimization algorithm and dynamic threshold evaluation are used to select the optimal solution. The system implementing this method includes a data processing module, a design analysis module, a solution optimization module, and an interactive output module. This invention effectively solves the problem of design-production disconnect through end-to-end data fusion, production feasibility verification, and closed-loop optimization, thereby improving product reliability and overall efficiency.

Description

Technical Field

[0001] This invention belongs to the field of intelligent product design technology, specifically relating to a product design assistance system and method based on big data. Background Technology

[0002] With increasing market competition and constantly evolving consumer demands, product design plays an increasingly important role in a company's success. Traditional product design methods often rely on the designer's experience and subjective judgment, which can be inherently uncertain and risky. Especially when facing a rapidly changing market and diverse consumer needs, traditional methods often struggle to respond and adjust quickly, leading to a disconnect between design solutions and actual market demands.

[0003] In traditional design processes, designers typically develop design solutions based on the product's shape, size, and materials. However, this approach often overlooks market dynamics and competitors' design directions. Market demand and product success often hinge on the ability to keep pace with market trends and meet specific consumer needs. However, due to a lack of systematic market data collection and analysis, design solutions often struggle to accurately predict market feedback, potentially leading to resource waste, increased risk of design failure, and an inability to maximize design value.

[0004] In recent years, with the development of big data technology, data-driven design methods have begun to receive widespread attention and application. Big data technology can provide accurate and scientific decision-making basis for product design by collecting and analyzing massive amounts of market data, consumer feedback, and competitor product information. Through big data analysis, the correlation between market trends, consumer preferences, and product characteristics can be deeply explored, enabling effective prediction of product market performance during the design phase and significantly improving the scientific nature and relevance of the design.

[0005] Chinese invention patent CN119313390A discloses a product design assistance system and method based on big data. This invention uses big data analysis and calculation to quickly identify potential design directions in the market, thereby shortening the design cycle and improving design efficiency. Based on market popularity data and similarity analysis, it reduces the risk of blind design, ensuring that the designed products better meet market demands. Through weighted analysis of local and overall product features, it ensures that the design scheme is more comprehensive and reasonable. With the support of big data, the designed products are more in line with market trends and consumer needs, enhancing the product's market competitiveness. Utilizing big data technology makes the design process more scientific and data-driven, reducing the uncertainty caused by subjective judgment. The provided reference 3D product data can provide valuable reference for subsequent detailed design and production, improving the efficiency and quality of the entire product development process.

[0006] However, in actual use, the aforementioned patents did not take into account production-side data such as material inventory, production process feasibility, and manufacturing costs, which may result in a design that is feasible to design but difficult to produce. Summary of the Invention

[0007] In view of the above-mentioned shortcomings in the existing technology, the present invention provides a product design assistance system and method based on big data to solve the problems in the background technology.

[0008] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0009] A product design assistance method based on big data includes the following steps:

[0010] S1, Full-link dynamic data acquisition and time-series preprocessing, collecting design feature data, market feedback data, similar product data, real-time production data and after-sales operation data of the target product, and cleaning, standardizing and structuring the above-mentioned collected data to obtain preprocessed data, while performing time series alignment and trend extraction on the time-series data with time dimension characteristics in the preprocessed data;

[0011] S2, Design Features and Market Demand Analysis: Extract design feature vectors reflecting the inherent attributes of the product from the preprocessed data, combine them with market popularity and user preference data contained in the time-series data, and obtain key design features and market demand trends through time-series attention mechanism analysis.

[0012] S3, Similar Product Matching and Evaluation: Based on the design feature vector, calculate the feature similarity between the target product and similar products in the preprocessed data; combine the functional semantic description in the similar product data to perform functional semantic analysis, generate a comprehensive similarity index that integrates feature similarity and functional semantic similarity, screen out highly matched similar products, and evaluate them from the dimensions of design reusability features, market performance adaptability, and fit with market demand trends.

[0013] S4, Preliminary design scheme generation: Based on the key design features, market demand trends, and evaluation results of similar products, a preliminary product design scheme is generated. Market constraints are embedded during the generation of the preliminary product design scheme, and the fit between the preliminary design scheme and the key features and the trend adaptability are quantitatively scored to form a verifiable scheme set.

[0014] S5, Design Scheme Optimization: Based on real-time production data and cross-domain knowledge graphs in the preprocessed data, the preliminary product design scheme is verified for production feasibility and optimized for multiple objectives to resolve conflicts between the preliminary design scheme and production conditions; at the same time, the time series analysis results of after-sales operation data are combined to provide feedback for the adjustment of design parameters.

[0015] S6, Optimization Scheme Evaluation and Output: The optimized design scheme is evaluated using dynamic thresholds, and a reference design scheme that meets the evaluation conditions and the basis for optimization are output.

[0016] Further, in step S1, the design feature data includes product structure parameters, functional parameters, and historical design scheme parameters; the market feedback data includes user reviews, competitor sales data, and market popularity trend data; the real-time production data includes material inventory data, production process parameter data, and manufacturing cost data; the after-sales operation data includes fault record data, user feedback data, and performance degradation data; the trend extraction of the time-series data uses a time series decomposition algorithm to separate long-term trend items, periodic items, and random items; the preprocessing includes: using a text fingerprint algorithm to remove duplicate data, using a clustering algorithm to identify and filter abnormal data, and using TF-IDF combined with LDA topic model to extract key information from unstructured data and perform structure transformation.

[0017] Furthermore, in step S2, the design feature vector includes functional features, structural features, material features, cost features, user experience features, and sustainability features; the temporal attention mechanism assigns dynamic attention weights to market data in different time periods, with recent data having a higher weight than older data.

[0018] Further, in step S3, the functional semantic analysis converts the functional description into semantic vectors using the BERT model and then calculates the cosine similarity; the formula for calculating the comprehensive similarity is: α is a dynamic adjustment coefficient, ranging from 0.4 to 0.6. α is dynamically adjusted according to the product type, with α ranging from 0.4 to 0.5 for technology-intensive products and from 0.5 to 0.6 for function-intensive products.

[0019] Furthermore, in step S4, the market constraints include market demand trend constraints, user preference weight constraints, and competitor parameter comparison constraints; the dimensions of the quantitative scoring include key feature coverage, trend matching degree, and cost controllability.

[0020] Furthermore, in step S5, the production feasibility verification specifically includes: material availability verification, which compares the material requirements of the design scheme with real-time inventory data, and triggers the retrieval of material alternatives when inventory is insufficient; process adaptability verification, which uses the process capability index to evaluate the matching degree between the design dimensional accuracy and the production line processing capability based on the production process parameter data; and cost controllability verification, which constructs a cost estimation model based on manufacturing cost data, and prioritizes adjusting high-cost features when the design scheme cost exceeds a threshold.

[0021] Furthermore, in step S5, the specific method for adjusting design parameters by using the time-series analysis results of after-sales operation data is to fit the performance degradation curve using an LSTM time-series prediction model to correct the design durability parameters; to use an association rule algorithm to mine the correlation between high-frequency faults and design features to optimize the design of faulty components; the multi-objective optimization adopts an improved Pareto optimization algorithm, and the objective function includes maximizing market adaptability, maximizing production feasibility, and maximizing cost-effectiveness, and includes a dynamic weight adjustment mechanism, which dynamically adjusts the weights of the objective function according to real-time data from the production end.

[0022] Furthermore, the triggering conditions for the dynamic weight adjustment mechanism include: increasing the weight of material substitution feasibility when production-side data shows insufficient material inventory; and the market adaptability rate. ,in Market characteristic weights and .

[0023] Further, in step S6, Market volatility is calculated based on the ratio of the standard deviation to the mean of competitor sales over the past 30 days. The baseline threshold is the average evaluation score of the best historical solutions for similar products, and λ is the adjustment coefficient. For fast-moving consumer goods, λ is 0.3, and for durable goods, λ is 0.1. The optimization basis includes the weight ratio of key features, production feasibility analysis, and feedback from after-sales data.

[0024] The present invention also provides a product design assistance system based on big data, used in the above-mentioned product design assistance method based on big data, comprising:

[0025] The data processing module includes a full-link dynamic data acquisition unit and a time-series preprocessing unit;

[0026] The design analysis module includes a feature extraction unit, a demand trend analysis unit, and a similar product matching evaluation unit;

[0027] The solution optimization module includes a production feasibility verification unit, an after-sales data feedback unit, and a multi-objective optimization unit, wherein the multi-objective optimization unit interacts with a cross-domain knowledge graph;

[0028] The interactive output module includes a preliminary scheme generation unit, a scheme evaluation unit, and a human-computer interaction unit, wherein the human-computer interaction unit provides a parameter adjustment interface.

[0029] Compared with the prior art, the present invention has the following advantages:

[0030] 1. Through the collaborative work of the end-to-end dynamic data acquisition module and the time series preprocessing module, comprehensive and dynamic utilization of design data is achieved. End-to-end data acquisition covers product design features, market feedback, real-time production data, and after-sales operation data. Combined with deduplication, anomaly filtering, and time series trend extraction in time series preprocessing, design decisions are based on complete dynamic data patterns.

[0031] 2. By integrating a production feasibility verification unit and a cross-domain knowledge graph into the solution optimization module, seamless integration between design and production is achieved. The production feasibility verification unit verifies the production adaptability of the solution during the design phase through material demand and inventory comparison, process capability index assessment, and cost estimation models. The cross-domain knowledge graph provides support for related knowledge such as material substitution and process adaptability, and can quickly retrieve alternative material solutions when inventory is insufficient, effectively resolving conflicts between design goals and production conditions.

[0032] 3. Through the closed-loop design of the after-sales data feedback unit and the multi-objective optimization unit, continuous improvement in product reliability and maximization of overall benefits are achieved. The after-sales data feedback unit transforms after-sales data into a basis for adjusting design parameters; the multi-objective optimization unit, based on an improved Pareto algorithm and a dynamic weight adjustment mechanism, balances market adaptability, production feasibility, and cost-effectiveness, and dynamically adjusts the optimization weights when material inventory fluctuates, ensuring that the solution meets market demands. Attached Figure Description

[0033] Figure 1 This is a flowchart of a product design assistance system and method based on big data according to the present invention;

[0034] Figure 2 This is a system framework diagram of a product design assistance system and method based on big data according to the present invention. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solution of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0036] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual images. They should not be construed as limiting the scope of this application. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0037] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present application. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0038] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0039] like Figure 1-2 As shown, this invention discloses a product design assistance method based on big data. It aims to address pain points in traditional product design, such as the disconnect between design and production and the difficulty in tracing after-sales issues, through end-to-end data fusion, time-series analysis, and multi-dimensional optimization, thereby improving the scientific rigor and feasibility of design solutions. Its core lies in driving the entire design process with data, combining time-series pattern mining and cross-domain knowledge support to form a closed-loop optimization mechanism from data collection to solution output. The specific implementation process is as follows:

[0040] S1, Full-link dynamic data acquisition and time-series preprocessing, collecting design feature data, market feedback data, similar product data, real-time production data and after-sales operation data of the target product, and cleaning, standardizing and structuring the above-mentioned collected data to obtain preprocessed data, while performing time series alignment and trend extraction on the time-series data with time dimension characteristics in the preprocessed data;

[0041] S2, Design Features and Market Demand Analysis: Extract design feature vectors reflecting the inherent attributes of the product from the preprocessed data, combine them with market popularity and user preference data contained in the time-series data, and obtain key design features and market demand trends through time-series attention mechanism analysis.

[0042] S3, Similar Product Matching and Evaluation: Based on the design feature vector, calculate the feature similarity between the target product and similar products in the preprocessed data; combine the functional semantic description in the similar product data to perform functional semantic analysis, generate a comprehensive similarity index that integrates feature similarity and functional semantic similarity, screen out highly matched similar products, and evaluate them from the dimensions of design reusability features, market performance adaptability, and fit with market demand trends.

[0043] S4, Preliminary design scheme generation: Based on the key design features, market demand trends, and evaluation results of similar products, a preliminary product design scheme is generated. Market constraints are embedded during the generation of the preliminary product design scheme, and the fit between the preliminary design scheme and the key features and the trend adaptability are quantitatively scored to form a verifiable scheme set.

[0044] S5, Design Scheme Optimization: Based on real-time production data and cross-domain knowledge graphs in the preprocessed data, the preliminary product design scheme is verified for production feasibility and optimized for multiple objectives to resolve conflicts between the preliminary design scheme and production conditions; at the same time, the time series analysis results of after-sales operation data are combined to provide feedback for the adjustment of design parameters.

[0045] S6, Optimization Scheme Evaluation and Output: The optimized design scheme is evaluated using dynamic thresholds, and a reference design scheme that meets the evaluation conditions and the basis for optimization are output.

[0046] In step S1, the full-link dynamic data acquisition and time-series preprocessing involves collecting product design feature data, market feedback data, similar product data, real-time production data, and after-sales operation data. The collected data is then cleaned, standardized, and structurally transformed. Simultaneously, time-series data undergoes time series alignment and trend extraction. This step is fundamental to the method, achieving real-time aggregation of multi-source heterogeneous data through the deployment of distributed data acquisition nodes, covering the entire product lifecycle: design feature data includes structural parameters, functional parameters, and technical specifications of historical design schemes; market feedback data covers user reviews, competitor sales data, and market trend data; real-time production data is synchronized from the Manufacturing Execution System (MES) and Enterprise Resource Planning (ERP) systems, including material inventory data, production process parameter data, and manufacturing cost data; and after-sales operation data is obtained through built-in product sensors or user feedback channels, including fault record data, user feedback data, and performance degradation data. After data collection, multi-dimensional preprocessing is performed: Text fingerprinting algorithms are used to remove duplicate data, such as removing duplicate user reviews from e-commerce platforms; clustering algorithms (such as K-means) are used to identify and filter outomas, such as abnormal parameter values ​​exceeding the 3σ range in production processes; unstructured data (such as user feedback text and fault description documents) are processed using TF-IDF combined with LDA topic modeling to extract key information and convert them into structured data. For time-series data (such as after-sales performance degradation data and production process parameter fluctuation data), time series decomposition algorithms (such as STL decomposition) are used for time series alignment and trend extraction, separating long-term trend items, periodic items, and random items, laying the foundation for subsequent dynamic pattern analysis.

[0047] Secondly, step S2, design feature and market demand analysis, is based on the preprocessed data obtained in step S1. Design feature vectors reflecting the inherent attributes of the product are extracted from the preprocessed data. Combined with market popularity data and user preference data contained in the time-series data, key design features and market demand trends are obtained through time-series attention mechanism analysis. The design feature vectors cover six dimensions: functional features (core functional indicators, completeness of additional functions), structural features (geometric dimensions, component connection methods), material features (raw material types, physical properties), cost features (R&D costs, material costs), user experience features (ease of operation, appearance satisfaction), and sustainability features (energy consumption level, recycling rate). The time-series attention mechanism assigns dynamic attention weights to market data from different time periods, with recent data having a higher weight than older data to capture the latest demand changes. Through time-series modeling, demand fluctuation patterns (such as seasonal preferences, technological iteration directions) are identified, ultimately outputting key design features and demand trends.

[0048] Furthermore, in step S3, similar product matching and evaluation, the feature similarity between the product to be designed and similar products is calculated based on the design feature vectors. This is combined with functional semantic analysis to obtain a comprehensive similarity score. Similar products with high reference value are then selected and evaluated. Feature similarity is calculated using Euclidean distance or cosine similarity algorithms, focusing on comparing the consistency of core parameters. Functional semantic analysis uses the BERT model to convert the functional description text of similar products into semantic vectors, and calculates the cosine similarity between the vectors to obtain the functional semantic similarity. The comprehensive similarity score is calculated using the following formula: α is a dynamic adjustment coefficient, and its specific value is determined through verification of historical matching accuracy of similar products, ranging from 0.4 to 0.6: for technology-intensive products, α is 0.4-0.5, focusing on feature parameter matching; for function-intensive products, α is 0.5-0.6, focusing on functional consistency. After screening similar products with high overall similarity, an evaluation is conducted from the dimensions of reusable design features, market performance adaptability, and alignment with market demand trends, outputting advantageous features and areas for improvement.

[0049] The value of the dynamic adjustment coefficient α (0.4-0.5 for technology-intensive products and 0.5-0.6 for function-intensive products) is determined based on a dual logic of product core value differentiation and practical verification.

[0050] For technology-intensive products (such as industrial inspection drones), whose core value relies on underlying technical parameters and performance indicators, user decisions are primarily based on these technical specifications. Examples include industrial inspection drones (which rely on flight accuracy, anti-interference levels, and other technical parameters) and precision medical equipment (which rely on detection accuracy, data processing algorithms, etc.). For these products, the technical characteristics (such as hardware parameters and core algorithm versions) have a weighting of ≥60% in their impact on product competitiveness; functional descriptions serve only as supplementary expressions of technical capabilities. For such products, if α=0.4, the feature similarity (technical parameter matching) weight accounts for 40%, which can accurately capture core technical differences such as flight accuracy (±0.5m) and anti-interference level (Class B). 120 project verifications show that the matching results have an 87% correlation with the technology iteration, ensuring the technical reference value of special material process adaptation at the production end (such as carbon fiber wing processing accuracy CPK=1.5) and after-sales fault tracing (signal interruption correlation 0.92). If α is increased to 0.6, the functional semantic similarity weight is too high (60%), and it is easy to match low technical parameter competitors (such as anti-interference level only Class A) due to functional descriptions such as "intelligent detection", resulting in the failure of key technology verification.

[0051] Function-intensive products (such as home smart robotic vacuum cleaners) focus on core value that users can directly perceive in terms of functional experience. User decisions for these products are primarily based on functional suitability. Examples include home smart robotic vacuum cleaners (relying on features like corner cleaning and battery life) and smart rice cookers (relying on features like even heating and recipe compatibility). For these products, functional features (such as "optimized corner cleaning" and "one-button operation") have a weighting of ≥60% in influencing user choice, while technical parameters (such as motor speed) only serve as support for functional implementation. For such products, when α=0.55 (in the range of 0.5-0.6), the weight of functional semantic similarity (such as matching user needs for "corner cleaning" and "intelligent obstacle avoidance") accounts for 45%. Statistics from 210 cases show that the functional needs and design features match 88%, effectively filtering out functional adaptation features such as "extendable side brush" and "optimized lithium battery capacity". If α drops to 0.4, the weight of technical features (such as motor speed and battery capacity) is too high (60%), which will weaken the matching priority of high-frequency functional needs such as "incomplete corner cleaning", causing similar product references to deviate from the core user experience.

[0052] Furthermore, step S4 generates preliminary design schemes based on the key design features obtained in step S2, market demand trends, and the similar product evaluation results in step S3. Multiple preliminary product design schemes, encompassing dimensions such as function, structure, and materials, are generated for further optimization. Market constraints are embedded during scheme generation, including market demand trend constraints, user preference weight constraints, and competitor parameter comparison constraints. Simultaneously, the fit and trend adaptability of the preliminary design schemes to key features are quantitatively scored, with scoring dimensions including key feature coverage, trend matching degree, and cost controllability, ultimately forming a verifiable set of schemes.

[0053] Furthermore, the design optimization in step S5 is a crucial step in improving the feasibility and adaptability of the design scheme. Based on real-time production data and cross-domain knowledge graphs in the preprocessed data, the preliminary product design scheme is verified for production feasibility and optimized for multiple objectives to resolve conflicts between design goals and production conditions; at the same time, the time-series analysis results of after-sales operation data are combined to provide feedback for adjusting design parameters.

[0054] The cross-domain knowledge graph covers material friction coefficients, supplier inventory, and process adaptation rules, and is automatically collected by connecting to supplier APIs and industry standard databases. New data is validated for compliance and outliers are removed through a domain expert rule base. An incremental update algorithm is used to expand the graph only for newly added entities and relationships.

[0055] The production feasibility verification includes three aspects:

[0056] Material availability verification compares the material requirements of the solution with inventory data, and if the inventory is insufficient, it retrieves alternative solutions through cross-domain knowledge graphs.

[0057] Process adaptability verification uses the process capability index CPK to evaluate the matching degree between the design accuracy and the production line capability. CPK≥1.33 is considered qualified.

[0058] Cost controllability verification constructs a cost estimation model based on manufacturing cost data, and preferentially adjusts high-cost features when the cost exceeds the threshold.

[0059] Secondly, after-sales data feedback fits the performance degradation curve through the LSTM time series prediction model to correct the design durability parameters; uses the association rule algorithm to mine the correlation between high-frequency failures and design features, and optimize the design of vulnerable components. Multi-objective optimization uses an improved Pareto optimization algorithm. The objective functions include maximizing the market adaptation rate, maximizing production feasibility, and maximizing cost-benefit. The market adaptation rate is calculated according to the following formula: , where is the market feature weight and ; The optimization process includes a dynamic weight adjustment mechanism - dynamically adjusts the weights of each objective function according to the real-time data at the production end. When the material inventory is insufficient, increases the weight of material substitution feasibility in the production feasibility objective function.

[0060] Furthermore, the optimization plan evaluation and output in step S6 use a dynamic threshold to evaluate the optimized design plan, and output a reference design plan that meets the evaluation conditions and the optimization basis. The dynamic threshold is calculated according to the following formula: ; Among them, the market volatility is calculated based on the ratio of the standard deviation to the mean of the sales volume of competing products in the past 30 days, that is ; The benchmark threshold is the average evaluation score of the historical optimal plan of similar products; λ is the adjustment coefficient, λ = 0.3 for fast-moving consumer goods and λ = 0.1 for durable goods to adapt to the market characteristics of different products. Finally, output a reference design plan that meets the evaluation conditions and the optimization basis. The optimization basis includes the proportion of key feature weights, production feasibility analysis, and after-sales data feedback description, providing comprehensive support for design decisions.

[0061] The rationality of the dynamic threshold calculation rule is verified through the demand differences and market characteristics of different product types: Taking a robot vacuum cleaner (durable goods, λ=0.1) and a fast-moving consumer good (such as a smart water bottle, λ=0.3) as an example, the robot vacuum cleaner has a long purchase decision cycle and relatively stable market demand. The ratio of the standard deviation of the sales of competing products to the mean in the past 30 days (market volatility) is usually low. Using λ=0.1 to calculate the dynamic threshold (dynamic threshold = benchmark threshold・(1+λ・market volatility)) can avoid excessive impact of short-term market fluctuations on the solution evaluation and ensure continuous attention to long-term value design features such as "corner cleaning optimization and battery life improvement"; while fast-moving consumer goods have fast consumption decisions and changeable market trends (such as the monthly turnover rate of the "social attribute function" of smart water bottles exceeding 30%), λ=0.3 can respond to market fluctuations in a timely manner and quickly select design solutions that fit the trend. In Example 1, the robotic vacuum cleaner, as a durable good, has a dynamic threshold of 85×(1+0.1×0.17)=86.45 points when λ is set to 0.1. This approach not only references the historical best solution (benchmark threshold) to ensure the design baseline, but also fine-tunes it through market volatility to adapt to market trends such as increased attention to intelligent obstacle avoidance. This allows the solution evaluation to both anchor the long-term value of the product and keenly capture iterative demand. Comparative verification shows that this value rule improves the accuracy of durable good solution evaluation, and achieves a 92% matching degree for trendy functions in the FMCG scenario. It accurately adapts to the market feedback logic of different product types, providing a scientific quantitative basis for solution optimization.

[0062] The present invention also discloses a product design assistance system based on big data, which is used to implement the above-mentioned product design assistance method based on big data. The system mainly consists of a data processing module, a design analysis module, a scheme optimization module and an interactive output module. The modules work together to form a design assistance closed loop.

[0063] The data processing module is used to execute step S1, including a full-link dynamic data acquisition unit and a time-series preprocessing unit: the full-link dynamic data acquisition unit acquires full-link data in real time through multi-source interfaces; the time-series preprocessing unit performs cleaning, standardization and structure transformation on the acquired data, and extracts trend features from the time-series data through time series analysis technology to provide high-quality data for subsequent modules.

[0064] Secondly, the design analysis module is used to execute steps S2-S3, including a feature extraction unit, a demand trend analysis unit, and a similar product matching evaluation unit: the feature extraction unit extracts design feature vectors covering six dimensions; the demand trend analysis unit analyzes market demand through a time-series attention mechanism model and outputs key design features; the similar product matching evaluation unit calculates feature similarity and functional semantic similarity, and selects and evaluates highly matched products according to the comprehensive similarity formula.

[0065] Meanwhile, the solution optimization module is the core optimization unit of the system, integrating the production feasibility verification unit, the after-sales data feedback unit, and the multi-objective optimization unit. It is used to execute step S5: the production feasibility verification unit verifies production feasibility through material inventory comparison, process capability index evaluation, and cost model; the after-sales data feedback unit outputs design parameter adjustment suggestions through time series prediction model and association rule algorithm; the multi-objective optimization unit adopts an improved Pareto optimization algorithm, with the goal of maximizing market adaptability, production feasibility, and cost-effectiveness, and adapts to changes in production data through a dynamic weight adjustment mechanism.

[0066] Finally, the interactive output module is used to execute steps S4-S6, including a preliminary solution generation unit, a solution evaluation unit, and a human-computer interaction unit: the preliminary solution generation unit generates a preliminary solution with embedded market constraints and quantifies and scores it; the solution evaluation unit uses dynamic thresholds to screen compliant solutions; the human-computer interaction unit outputs reference solutions and optimization basis, and provides parameter adjustment interfaces to support manual optimization.

[0067] Example 1:

[0068] Taking the design optimization of a household intelligent robotic vacuum cleaner as an example, the implementation process of this invention will be further explained:

[0069] During the end-to-end data acquisition and time-series preprocessing phase, the data processing module collects data from multiple sources: design feature data includes suction power, battery life, and navigation accuracy of existing models; market feedback data covers user reviews on e-commerce platforms over the past year, competitor sales rankings, and feature search trends; production-side data is synchronized from the factory system, including lithium battery inventory, motor assembly process parameters, and unit manufacturing cost targets; after-sales data is obtained through the product app, including fault records, performance degradation data, and user usage scenario distribution. In preprocessing, duplicate reviews are removed, abnormal process parameters are filtered, and user reviews are converted into structured topics; after-sales performance degradation data is decomposed into a time series to extract long-term trends, periodic items, and random items, providing data support for subsequent analysis.

[0070] In the design feature and requirements analysis phase, the design analysis module extracts design feature vectors, covering six dimensions: function, structure, materials, cost, user experience, and sustainability. By assigning dynamic weights to market data through a temporal attention mechanism, the analysis identifies corner cleaning, battery life, obstacle avoidance accuracy, and protection in humid environments as key design features. Among these, the user attention weights for corner cleaning and intelligent obstacle avoidance have increased to 0.35 and 0.28 respectively in the past three months.

[0071] In the similar product matching and evaluation phase, 15 competing products in the same price range were selected, and feature similarity and functional semantic similarity were calculated. Since robotic vacuum cleaners are function-intensive products, a dynamic adjustment coefficient of 0.55 was used. Two highly matched reference products were selected according to the comprehensive similarity formula, and their retractable side brushes, optimized lithium battery capacity, and waterproof rating were listed as reusable advantageous features.

[0072] In the preliminary design phase, three schemes were generated based on key features and evaluation results of similar products: a performance-first scheme that enhances suction power and battery life, an experience-first scheme that optimizes the side brush and obstacle avoidance algorithm, and a cost-first scheme that adopts a single battery plus a high-efficiency motor combination. After embedding market constraints, the scores were quantified, and the experience-first and cost-first schemes formed a verifiable set.

[0073] During the design optimization phase, production feasibility verification revealed insufficient brush material inventory for the experience-first solution. Equivalent alternative materials were found through cross-domain knowledge graph retrieval. Process compatibility verification confirmed dimensional accuracy was acceptable. Cost verification, through sensor replacement, brought costs within a threshold. Post-sales data feedback suggested improving battery protection levels by fitting the degradation curve using a time-series model. Association rule analysis revealed that drive wheel jamming was related to the material, recommending replacement with a wear-resistant material. Multi-objective optimization employed a modified Pareto algorithm. Due to lithium battery inventory shortages, dynamic weight adjustments increased the production feasibility weight, ultimately resulting in the highest overall score for the experience-first solution.

[0074] In the optimization scheme evaluation and output phase, the calculated dynamic threshold was 86.45 points, and the experience-first scheme achieved a score of 89.3 points, meeting the standard. The output included a reference design scheme and optimization basis, including key feature weights, production feasibility analysis, and after-sales feedback. Designers adjusted the side brush extension length through an interactive interface, and the system updated parameters in real time to complete the final design.

[0075] As can be seen from this embodiment, the present invention achieves precise adaptation of the design scheme to market demand and production conditions through full-link data-driven and multi-dimensional optimization, verifying the practicality of the method and system.

[0076] The above are merely embodiments of the present invention. The circuits, electronic components, and modules involved are all prior art, fully achievable by those skilled in the art, and require no further explanation. The scope of protection in this application does not involve improvements to the software and methods. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all prior art in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent.

Claims

1. A product design assistance method based on big data, characterized in that: Includes the following steps: S1, Full-link dynamic data acquisition and time-series preprocessing, collecting design feature data, market feedback data, similar product data, real-time production data and after-sales operation data of the target product, and cleaning, standardizing and structuring the above-mentioned collected data to obtain preprocessed data, while performing time series alignment and trend extraction on the time-series data with time dimension characteristics in the preprocessed data; S2, Design Features and Market Demand Analysis: Extract design feature vectors reflecting the inherent attributes of the product from the preprocessed data, combine them with market popularity and user preference data contained in the time-series data, and obtain key design features and market demand trends through time-series attention mechanism analysis. S3, Similar Product Matching and Evaluation: Based on the design feature vector, calculate the feature similarity between the target product and similar products in the preprocessed data; combine the functional semantic description in the similar product data to perform functional semantic analysis, generate a comprehensive similarity index that integrates feature similarity and functional semantic similarity, screen out highly matched similar products, and evaluate them from the dimensions of design reusability features, market performance adaptability, and fit with market demand trends. S4, Preliminary design scheme generation: Based on the key design features, market demand trends, and evaluation results of similar products, a preliminary product design scheme is generated. Market constraints are embedded during the generation of the preliminary product design scheme, and the fit between the preliminary design scheme and the key features and the trend adaptability are quantitatively scored to form a verifiable scheme set. S5, Design Scheme Optimization: Based on real-time production data and cross-domain knowledge graphs in the preprocessed data, the preliminary product design scheme is verified for production feasibility and optimized for multiple objectives to resolve conflicts between the preliminary design scheme and production conditions. The production feasibility verification specifically includes three aspects: material availability verification, process adaptability verification, and cost controllability verification; at the same time, the time-series analysis results of after-sales operation data are combined to provide feedback for the adjustment of design parameters. S6, Optimization Scheme Evaluation and Output: The optimized design scheme is evaluated using dynamic thresholds, and a reference design scheme that meets the evaluation conditions and the basis for optimization are output.

2. The product design assistance method based on big data as described in claim 1, characterized in that: In step S1, the design feature data includes product structure parameters, functional parameters, and historical design scheme parameters; the market feedback data includes user reviews, competitor sales data, and market popularity trend data; and the real-time production data includes material inventory data, production process parameter data, and manufacturing cost data. The after-sales operation data includes fault record data, user feedback data, and performance degradation data. The trend extraction of the time-series data uses a time series decomposition algorithm to separate long-term trend items, periodic items, and random items; the preprocessing includes: using a text fingerprint algorithm to remove duplicate data, using a clustering algorithm to identify and filter abnormal data, and using TF-IDF combined with LDA topic model to extract key information from unstructured data and perform structure transformation.

3. The product design assistance method based on big data as described in claim 1, characterized in that: In step S2, the design feature vector includes functional features, structural features, material features, cost features, user experience features, and sustainability features; the temporal attention mechanism assigns dynamic attention weights to market data in different time periods, with recent data having a higher weight than older data.

4. The product design assistance method based on big data as described in claim 1, characterized in that: In step S3, the functional semantic analysis converts the functional description into semantic vectors using the BERT model and then calculates the cosine similarity; the formula for calculating the comprehensive similarity is: α is a dynamic adjustment coefficient, ranging from 0.4 to 0.

6. α is dynamically adjusted according to the product type, with α ranging from 0.4 to 0.5 for technology-intensive products and from 0.5 to 0.6 for function-intensive products.

5. The product design assistance method based on big data as described in claim 1, characterized in that: In step S4, the market constraints include market demand trend constraints, user preference weight constraints, and competitor parameter comparison constraints; the dimensions of the quantitative scoring include key feature coverage, trend matching degree, and cost controllability.

6. The product design assistance method based on big data as described in claim 1, characterized in that: In step S5, the material availability verification involves comparing the material requirements of the design scheme with real-time inventory data, and triggering a material alternative search when the inventory is insufficient; the process adaptability verification involves using the process capability index to evaluate the matching degree between the design dimensional accuracy and the production line processing capability based on the production process parameter data. Cost controllability verification involves building a cost estimation model based on manufacturing cost data, and prioritizing the adjustment of high-cost features when the cost of the design exceeds a threshold.

7. The product design assistance method based on big data as described in claim 1, characterized in that: In step S5, the specific method for adjusting design parameters based on the time-series analysis results of after-sales operation data is as follows: fitting the performance degradation curve using an LSTM time-series prediction model to correct the design durability parameters; using an association rule algorithm to mine the correlation between high-frequency faults and design features to optimize the design of faulty components; the multi-objective optimization adopts an improved Pareto optimization algorithm, and the objective function includes maximizing market adaptability, maximizing production feasibility, and maximizing cost-effectiveness, and includes a dynamic weight adjustment mechanism, which dynamically adjusts the weights of the objective function based on real-time data from the production end.

8. The product design assistance method based on big data as described in claim 7, characterized in that: The triggering conditions for the dynamic weight adjustment mechanism include: increasing the weight of material substitution feasibility when production-side data shows insufficient material inventory; and the market adaptability rate. ,in Market characteristic weights and .

9. The product design assistance method based on big data as described in claim 1, characterized in that: In step S6, Market volatility is calculated based on the ratio of the standard deviation to the mean of competitor sales over the past 30 days. The baseline threshold is the average evaluation score of the best historical solutions for similar products, and λ is the adjustment coefficient. For fast-moving consumer goods, λ is 0.3, and for durable goods, λ is 0.

1. The optimization basis includes the weight ratio of key features, production feasibility analysis, and feedback from after-sales data.

10. A product design assistance system based on big data, used in the product design assistance method based on big data as described in any one of claims 1 to 9, characterized in that, include: The data processing module includes a full-link dynamic data acquisition unit and a time-series preprocessing unit; The design analysis module includes a feature extraction unit, a demand trend analysis unit, and a similar product matching evaluation unit; The solution optimization module includes a production feasibility verification unit, an after-sales data feedback unit, and a multi-objective optimization unit, wherein the multi-objective optimization unit interacts with a cross-domain knowledge graph; The interactive output module includes a preliminary scheme generation unit, a scheme evaluation unit, and a human-computer interaction unit, wherein the human-computer interaction unit provides a parameter adjustment interface.

Images