Design optimization method and device based on big data analysis, equipment and storage medium

Abstract

The invention relates to a design optimization method based on big data analysis, and the method comprises the following steps: carrying out the improved point recognition of clustering analysis features through an improved point recognition algorithm, obtaining an improved point set, carrying out the primary optimization of a preliminary design scheme according to the recognized improved point set, and obtaining a first optimization design scheme; predicting the market demand of the first optimization design scheme to obtain a market demand prediction result; performing value evaluation on the market demand prediction result to obtain a value evaluation result; according to the method, association rule mining is carried out on a first optimization design scheme to obtain an improved strategy, and secondary optimization is carried out on the first optimization design scheme according to the improved strategy to obtain a second optimization design scheme, so that the problem that most traditional methods are lack of systematic association rule mining and improved strategy generation mechanisms is solved; the technical problems that in the iteration process of design optimization, key improvement points cannot be accurately recognized, the optimization process is delayed, and the development cost is increased are solved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a design optimization method, device, equipment and storage medium based on big data analysis. Background Art

[0002] In the current product design and development process, with the intensification of market competition and the diversification of consumer demand, companies are increasingly relying on big data technology to assist decision-making. Big data analysis provides the ability to extract valuable information from massive data, making the optimization of design solutions more accurate and efficient. However, traditional design optimization methods often rely on experience and trial and error, and cannot fully utilize data-driven insights, which may result in the design solution not achieving the expected results in the actual market, or even the risk of failure. Therefore, how to effectively integrate big data analysis in the design process and optimize the solution in real time has become an important direction of current research.

[0003] Although big data technology has been applied in many fields, there are still certain challenges in its specific application in product design optimization. First of all, big data analysis often faces problems such as uneven data quality and complex data dimensions, which makes it difficult to extract meaningful design features and perform reasonable clustering. In addition, changes in market demand are often highly uncertain and dynamic, and traditional forecasting methods are difficult to cope with complex market environments. This requires that the market demand forecasting algorithm in the design optimization process be more flexible and accurate in order to provide a strong market orientation for the design solution.

[0004] At the same time, in the process of design optimization, how to make timely adjustments and conduct secondary optimization when the initial optimization results are found to be unsatisfactory is also a difficulty in current research. Most traditional methods lack a systematic association rule mining and improvement strategy generation mechanism, which leads to the inability to accurately identify key improvement points during the iterative process of design optimization, thereby delaying the optimization process and increasing development costs. Therefore, the design optimization method based on big data analysis aims to effectively solve the shortcomings of traditional design optimization methods through steps such as cluster analysis, improvement point identification, and association rule mining, and improve the competitiveness and success rate of design solutions in the actual market. Summary of the invention

[0005] The main purpose of the present invention is to provide a design optimization method, device, equipment and storage medium based on big data analysis, which solves the technical problem that most traditional methods lack a systematic association rule mining and improvement strategy generation mechanism, which leads to the inability to accurately identify key improvement points during the iterative process of design optimization, thereby delaying the optimization process and increasing development costs.

[0006] To achieve the above object, the present invention provides a design optimization method based on big data analysis, comprising the following steps: Obtaining a preliminary design scheme through a user, and extracting scheme features from the preliminary design scheme to obtain scheme features; Performing cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption; By using an improvement point identification algorithm, the cluster analysis feature is identified with improvement points to obtain an improvement point set, and the preliminary design scheme is optimized once according to the identified improvement point set to obtain a first optimized design scheme; Using a preset market demand algorithm, the market demand forecasting of the first optimized design solution is performed to obtain a market demand forecasting result; wherein the market demand forecasting result includes the potential market size, expected sales volume and target customer group; Performing a value assessment on the market demand forecast result to obtain a value assessment result; When the value assessment result is not within a preset value range, association rule mining is performed on the first optimized design scheme to obtain an improvement strategy, and the first optimized design scheme is secondary optimized according to the improvement strategy to obtain a second optimized design scheme.

[0007] Furthermore, the preliminary design scheme is subjected to scheme feature extraction to obtain scheme features, including: Obtaining the design goals of the preliminary design plan, and performing a demand analysis on users based on the design goals to obtain user needs; wherein the user needs include design purposes and expected results; Based on the user needs, list the functional requirements of the preliminary design solution; Conducting feasibility judgment on the preliminary design scheme based on the functional requirements list to obtain a feasibility judgment result; If the feasibility judgment result is that the preliminary design scheme is feasible, then scheme feature extraction is performed on the preliminary design scheme to obtain scheme features.

[0008] Furthermore, cluster analysis is performed on the scheme features to obtain cluster analysis features, including: By using a preset clustering algorithm, the feature vector of the scheme features is normalized to obtain a feature vector set; Performing feature vector screening on the feature vector set by using an information gain method to obtain a screened feature vector set; Performing feature vector expansion processing on the filtered feature vector set to obtain an expanded feature vector set; Performing vector space dimensionality reduction on the extended feature vector set to obtain a reduced-dimensional feature vector set; Performing Euclidean distance calculation on the reduced dimension feature vector set to capture similarity feature vectors at multiple scales; Perform vector fusion on similarity feature vectors at multiple scales to generate a similarity feature vector; Vector feature analysis is performed on the similarity feature vector to obtain cluster analysis features.

[0009] Further, the cluster analysis features are identified for improvement points by an improvement point identification algorithm to obtain an improvement point set, and the preliminary design scheme is optimized once according to the identified improvement point set to obtain a first optimized design scheme, including: Inputting the cluster analysis features into a preset improvement point identification algorithm to identify improvement points and obtain an improvement point set; Calculating the weight of the set of improvement points to obtain the priority ranking of each improvement point in the set of improvement points; Optimize the preliminary design scheme once based on the priority-ranked improvement points to obtain a preliminary optimization scheme; Constructing a corresponding objective function based on the design goal; Based on a preset Pareto optimization algorithm, multi-objective optimization is performed on the preliminary optimization scheme based on the objective function to obtain a preliminary non-dominated solution set; Based on a preset fitness function, each solution in the preliminary non-dominated solution set is analyzed and compared to obtain a Pareto frontier solution set; Based on the Pareto front solution set, an in-depth analysis is performed on the design goal conflicts existing in the preliminary optimization scheme to obtain a conflict analysis report; The preliminary optimization scheme is adjusted according to the preset constraint conditions and the conflict analysis report to obtain a first optimized design scheme.

[0010] Furthermore, the market demand forecasting result is obtained by forecasting the market demand of the first optimization design scheme through a preset market demand algorithm, including: Extracting market demand features from the first optimization design solution using a preset market demand algorithm to obtain a feature set for market demand prediction; Performing time series analysis on the feature set of the market demand forecast to identify trend changes in future market demand and obtain market demand trend forecast results; Performing regression analysis on the first optimized design solution based on the market demand trend forecast result to obtain a market demand-solution feature correlation; Based on the preset Bayesian network model, the uncertainty in the market demand is inferred based on the market demand-solution feature correlation to obtain the probability distribution of demand forecast; wherein the uncertainty includes market volatility, uncertainty in consumer behavior, competitive situation, speed of technological innovation and supply chain risk; By using an error evaluation method, the market demand trend forecast result is verified and optimized based on the probability distribution of the demand forecast, so as to obtain an optimized market demand forecast result.

[0011] Furthermore, the market demand forecast result is evaluated for value, and a value evaluation result is obtained, including: Through a preset revenue forecasting model, the market demand forecasting results are analyzed for revenue, and a potential revenue evaluation result is obtained; wherein the potential revenue evaluation result includes potential sales, profit margin and market share; Conduct market competitiveness analysis based on the potential revenue assessment results to obtain a competitiveness index; Conduct consumer acceptance analysis based on the competitiveness index and obtain consumer acceptance scores; Evaluate potential risk factors in the market based on consumer acceptance scores and obtain a risk assessment report; Calculate the return on investment based on the risk assessment report to obtain the return on investment; The performance of the first optimized design solution in the market life cycle is analyzed based on the return on investment to obtain a market life cycle curve; Analyze brand influence based on the market life cycle curve to obtain the brand influence index; Conduct market expansion assessment based on the brand influence index and obtain a market expansion potential report; Perform a value assessment on the market expansion potential report to obtain a value assessment result.

[0012] Furthermore, when the value assessment result is not within a preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy, and the first optimization design scheme is optimized again according to the improvement strategy to obtain a second optimization design scheme, including: Based on the value assessment result, a comparison is performed against a preset value range to obtain a deviation analysis result; When the deviation analysis result shows that the value assessment result is not within the preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy; Based on the improvement strategy, the first optimized design solution is optimized for a second time to obtain a second optimized design solution; Re-evaluate the market demand forecast result based on the second optimized design solution to obtain a new value evaluation result; Until the new value assessment result is within the preset value range.

[0013] The present invention also provides a design optimization device based on big data analysis, comprising: An acquisition module is used to acquire a preliminary design scheme from a user, and extract scheme features from the preliminary design scheme to obtain scheme features; An analysis module, used for performing cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption; An identification module, used to identify improvement points of the cluster analysis features through an improvement point identification algorithm to obtain an improvement point set, and optimize the preliminary design scheme once according to the identified improvement point set to obtain a first optimized design scheme; A prediction module, used to perform market demand prediction on the first optimized design solution through a preset market demand algorithm to obtain a market demand prediction result; wherein the market demand prediction result includes a potential market size, expected sales volume, and a target customer group; An evaluation module, used to perform a value evaluation on the market demand forecast result to obtain a value evaluation result; The improvement module is used to perform association rule mining on the first optimization design scheme to obtain an improvement strategy when the value assessment result is not within a preset value range, and to perform secondary optimization on the first optimization design scheme according to the improvement strategy to obtain a second optimization design scheme.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The design optimization method based on big data analysis provided by the present invention comprises the following steps: obtaining a preliminary design scheme through a user, and extracting scheme features of the preliminary design scheme to obtain scheme features; performing cluster analysis on the scheme features to obtain cluster analysis features; performing improvement point identification on the cluster analysis features through an improvement point identification algorithm to obtain an improvement point set, and optimizing the preliminary design scheme once according to the identified improvement point set to obtain a first optimized design scheme; performing market demand forecasting on the first optimized design scheme through a preset market demand algorithm to obtain a market demand forecast result; performing value assessment on the market demand forecast result to obtain a value assessment result; when the value assessment result is not within a preset value range, performing association rule mining on the first optimized design scheme to obtain an improvement strategy, and performing secondary optimization on the first optimized design scheme according to the improvement strategy to obtain a second optimized design scheme. Through the above-mentioned technical means, the lack of systematic association rule mining and improvement strategy generation mechanism in most traditional methods is solved, which leads to the technical problem that key improvement points cannot be accurately identified in the iterative process of design optimization, thereby delaying the optimization process and increasing the development cost, and the whole method is based on big data analysis and fully utilizes the power of data to optimize the scheme. This technical feature makes the decision-making process more scientific and objective, reduces the human bias in traditional design optimization methods, and improves the competitiveness and success rate of design solutions in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of the steps of a design optimization method based on big data analysis in one embodiment of the present invention; Figure 2 is a structural block diagram of a design optimization device based on big data analysis in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 is a schematic diagram of the steps of a design optimization method based on big data analysis in one embodiment of the present invention; In one embodiment of the present invention, a design optimization method based on big data analysis is provided, comprising the following steps: Step S1, obtaining a preliminary design scheme through a user, and extracting scheme features from the preliminary design scheme to obtain scheme features.

[0021] Specifically, the above steps involve the key links in the design process, which not only lays the foundation for subsequent design optimization, but also provides a clear direction for further improvement. When explaining this step in detail, it is necessary to fully understand the relationship between the preliminary design plan, solution feature extraction and solution features, as well as the role they play in the entire design process. First of all, obtaining the preliminary design plan from the user is the starting point of the entire process. The preliminary design plan can be understood as the basic design concept or model conceived by the user or designer in the early stage of the project. It contains information such as design goals, basic functions, and possible implementation paths. This design plan is often based on the designer's initial understanding of the problem and the initial idea of ​​the design goal. It can be a sketch, a preliminary CAD model, or even a design concept described orally or in writing. However, this preliminary design plan is often rough and not deeply optimized, so further analysis and refinement are required to identify the key features therein. When it comes to "extracting solution features from the preliminary design plan", this process is actually deconstructing and analyzing the preliminary design plan in order to extract features that are critical to the design results. These features are usually core parameters or indicators that can affect the design performance, and may include geometric dimensions, material properties, functional requirements, operating procedures, user interaction methods, etc. For example, when designing a new smart watch, the preliminary design plan may include the size of the case, the resolution of the display, the type and number of built-in sensors, etc. When extracting solution features, it is necessary to identify from this information which parameters have the greatest impact on the performance of the watch, such as the waterproof performance of the case, the accuracy of the sensor, the energy consumption of the display, etc. These key features will directly affect the final use effect and market competitiveness of the watch. The "solution features" obtained through solution feature extraction can be understood as the essence of the preliminary design plan, and they are the core basis for further design optimization. These solution features are not just a simple refinement of the preliminary design plan, they also need to be quantified and modeled through scientific methods so that they can be effectively used in the subsequent optimization process. For example, in the example of the smartwatch above, if the energy consumption of the display screen is obtained as a key feature through solution feature extraction, then we may use a specific numerical model to express this energy consumption feature, such as the power consumption curve under different brightness conditions, so that in the subsequent optimization process, the designer can reduce the energy consumption of the watch by adjusting the display brightness or selecting low-power display technology, thereby improving its battery life. Furthermore, solution feature extraction is not just a passive process, it is actually an interaction between the designer and the design object. In this process, the designer needs to constantly communicate with the preliminary design plan, and identify the most critical features for the design goals through analysis and comparison.At the same time, solution feature extraction also requires designers to have certain domain knowledge and analytical capabilities, because only by fully understanding the working principle and use environment of the design object can key features be effectively identified. For example, when designing a new energy vehicle, designers need to consider a series of features closely related to the performance of new energy vehicles, such as the energy density, charging time, and cruising range of the battery pack. In the process of solution feature extraction, designers will analyze the parameters of the battery pack's thermal management system, the efficiency of the powertrain system, the body aerodynamic design, and other aspects, and finally extract several key features that have the greatest impact on the performance of the vehicle. In summary, obtaining a preliminary design solution through users and extracting its solution features is a process of transforming rough design ideas into operational design elements. This process not only lays the foundation for design optimization, but also provides a clear direction for subsequent improvements. The solution features obtained through solution feature extraction will become an important basis for subsequent design optimization, helping designers make more scientific and effective decisions in the subsequent design process, so as to finally obtain a design solution with better performance and better user experience. This process reflects a key turning point from concept to implementation of design, ensuring the scientificity, rationality and feasibility of the design.

[0022] Step S2, performing cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption.

[0023] Specifically, the above steps are to classify multiple scheme features extracted from the preliminary design scheme through cluster analysis, so as to better understand and optimize the key influencing factors in the design process. In this process, the designer first classifies the extracted scheme features according to their similarity and influence through cluster analysis technology, thereby obtaining several main cluster analysis features. These features include cost, efficiency and energy consumption, which means that all scheme features are classified into cost-related features, efficiency-related features and energy-related features. For example, when designing a smart watch, cluster analysis may classify cost-related features such as case material and manufacturing process into one category, efficiency-related features such as sensor accuracy and processor speed into another category, and energy-related features such as battery capacity and display power consumption into a third category. In this way, the designer can adjust the features in a specific category in a targeted manner in the subsequent optimization process, so as to optimize the design goals without affecting other categories. This not only simplifies the optimization process, but also more intuitively evaluates and improves the performance of the design scheme in terms of cost, efficiency and energy consumption, and achieves comprehensive optimization and improvement of the design.

[0024] Step S3, identifying improvement points of the cluster analysis features through an improvement point identification algorithm to obtain an improvement point set, and optimizing the preliminary design scheme once according to the identified improvement point set to obtain a first optimized design scheme.

[0025] Specifically, the purpose of the above steps is to further refine specific improvement points that can improve the design scheme through the improvement point identification algorithm based on cluster analysis. Specifically, the improvement point identification algorithm identifies possible deficiencies or optimization spaces in the design through in-depth analysis of cluster analysis features. These deficiencies or optimization spaces are the improvement point set. After obtaining the improvement point set, the designer can optimize and adjust the preliminary design scheme in a targeted manner. For example, in the design of a smart watch, if the improvement point identification algorithm finds that the small battery capacity is a major improvement point in the energy consumption cluster, then the designer can consider using a more efficient battery or optimizing the power management system to improve the battery life without significantly increasing costs or reducing efficiency. Through such optimization, the preliminary design scheme is adjusted and improved to form a first optimized design scheme, which has obvious improvements in performance, cost, efficiency or energy consumption compared to the preliminary design scheme, so as to better meet the design goals and user needs.

[0026] Step S4, using a preset market demand algorithm, conduct market demand forecasting on the first optimized design solution to obtain a market demand forecasting result; wherein the market demand forecasting result includes the potential market size, expected sales volume, and target customer group.

[0027] Specifically, the purpose of the above steps is to analyze and predict the optimized design scheme at the market level by using the market demand algorithm. Specifically, the market demand algorithm predicts the performance of the scheme in the market by analyzing market data, industry trends, consumer behavior and other factors, combined with the characteristics of the first optimized design scheme. First, the market demand algorithm will evaluate the potential market size of the first optimized design scheme based on the current market trends and consumer preferences. This includes identifying the extent to which the design scheme can meet market demand and the market scope that may be covered. For example, in the scenario of smart watch design, the market demand algorithm may analyze the current growth trend of the smart watch market, the growth of consumer demand for health monitoring functions, and the market performance of competitors, so as to predict the potential scale of this optimized smart watch in the market. Then, the algorithm will further predict the expected sales volume of the design scheme. This part involves a comprehensive evaluation of product pricing strategies, sales channel selection, and market promotion efforts, and gives a reasonable expected sales volume in combination with the potential market size. For example, if the market demand algorithm predicts that the smart watch in the first optimized design scheme has a high cost-effectiveness and the health monitoring function is favored by the target customer group, then the expected sales volume may be more optimistic. Finally, the market demand forecast results also include an analysis of the target customer groups. This part is based on the in-depth analysis of consumer behavior data by the market demand algorithm to identify the customer groups most likely to purchase the product. This may involve an analysis of consumer age, income level, lifestyle, and consumption habits. For example, if the algorithm finds that young professionals and fitness enthusiasts have a greater demand for smart watches, these groups will be identified as target customer groups. Through this market demand forecast, designers can better understand the potential and challenges of the first optimized design solution in the market, thereby providing an important reference for subsequent product launches, marketing, and sales strategy formulation. Ultimately, this step helps ensure that the design solution is not only feasible on a technical level, but also has strong competitiveness and broad development prospects in the market.

[0028] Step S5, performing value assessment on the market demand forecast result to obtain a value assessment result.

[0029] Specifically, the purpose of the above steps is to provide a quantitative judgment on the economic performance of the design solution in the market through value assessment analysis based on the market demand forecast. Specifically, the value assessment process comprehensively considers the potential market size, expected sales volume and target customer groups in the market demand forecast results, and combines factors such as cost, pricing strategy, competitor performance and industry environment to evaluate the expected benefits and long-term value of the product in the market. First, the value assessment will calculate the potential market benefits of the design solution based on the potential market size and expected sales volume in the market demand forecast results. For example, in the application scenario of smart watches, if the market demand forecast shows that the product has huge market potential in the field of health monitoring and high expected sales volume, then the value assessment will be based on this to estimate the sales revenue of the product. Combined with different pricing strategies, the assessment will also consider the cost structure and calculate the possible profit margin. At the same time, the value assessment is not limited to direct financial benefits, but also considers the long-term value and brand influence of the product in the market. This includes the analysis of the loyalty of the target customer group and the product usage cycle. For example, if market demand forecasts reveal that young fitness enthusiasts have a continuous demand for smart watches and are highly loyal, then the value assessment will believe that this product has a high long-term market value, which is not only reflected in the initial sales volume, but also in the subsequent market extension and brand recognition. In addition, the value assessment will also analyze the competitiveness of the design solution in combination with the market competition environment. This includes comparing the pricing, functions and market performance of competitors' products to determine the positioning and differentiation advantages of the design solution in the market. For example, if the value assessment results show that the smart watch in the design solution has obvious advantages in function and the pricing strategy is also competitive, then this solution may occupy a favorable position in the market, thereby improving the overall value expectations. Through this series of evaluations, the final value assessment results can provide a scientific basis for the commercialization decision of the design solution. Based on this result, the designer can further optimize the product design or adjust the market strategy to maximize the performance of the product in the market. In short, the purpose of this step is to transform the market demand forecast results into specific value judgments through multi-dimensional analysis to ensure that the design solution has strong economic returns and strategic advantages when entering the market.

[0030] Step S6, when the value assessment result is not within the preset value range, the first optimization design scheme is mined based on association rules to obtain an improvement strategy, and the first optimization design scheme is optimized again based on the improvement strategy to obtain a second optimization design scheme.

[0031] Specifically, the core purpose of the above steps is to ensure that the market value of the design scheme meets the expected standards. If the value assessment results in the previous step show that the scheme fails to reach the pre-set value range, the design scheme needs to be further analyzed and optimized to improve its market value. First, when the value assessment result is lower than expected, it means that the current design scheme may not fully meet the market demand in some aspects or has deficiencies in market competition. Therefore, the designer will use association rule mining technology to conduct an in-depth analysis of the first optimized design scheme. Association rule mining is a data mining technology that aims to discover the potential correlations and influence patterns between different design features. By analyzing these correlations, designers can identify which design features or combinations may lead to unsatisfactory value assessment results. For example, in the design of smart watches, if it is found that there is a negative correlation between battery life and certain high-power consumption functions, and this correlation affects the market value, then this is a key point that needs to be improved. Then, the improvement strategy obtained through association rule mining will provide designers with specific optimization directions. For example, if the mining results show that by adjusting the operating mode of certain high-power consumption functions or optimizing the battery management system, the battery life can be significantly improved, thereby improving the market value of the product, then this strategy will become the basis for the secondary optimization of the design scheme. Based on the identified improvement strategies, the designer conducts a second optimization of the first optimized design. This optimization process not only involves specific technical improvements, but may also include re-evaluating the cost structure, adjusting the functional configuration, or improving the user experience. For example, in the application scenario of smart watches, designers may optimize software algorithms to reduce the energy consumption of certain functions while maintaining their performance to improve battery life and meet the market demand for long-lasting smart devices. Ultimately, the second-optimized design, that is, the second-optimized design, will perform closer to or reach the pre-set value range in the value assessment, thereby improving its market competitiveness and economic returns. This cyclic optimization process ensures that the design is not only technically feasible, but also successful in the market, so that the product can better meet market demand and achieve the expected business goals.

[0032] In a specific embodiment, the preliminary design scheme is subjected to scheme feature extraction to obtain scheme features, including: Obtaining the design goals of the preliminary design plan, and performing a demand analysis on users based on the design goals to obtain user needs; wherein the user needs include design purposes and expected results; Based on the user needs, list the functional requirements of the preliminary design solution; Conducting feasibility judgment on the preliminary design scheme based on the functional requirements list to obtain a feasibility judgment result; If the feasibility judgment result is that the preliminary design scheme is feasible, then scheme feature extraction is performed on the preliminary design scheme to obtain scheme features.

[0033] "Specifically," the purpose of this step is to ensure that the preliminary design scheme is reasonable and feasible in terms of technology and market requirements through systematic analysis and evaluation, and finally to extract the scheme features with guiding significance to provide a basis for subsequent optimization and improvement. First of all, before extracting the scheme features of the preliminary design scheme, it is necessary to clarify the design goal of the scheme. This design goal is usually set based on the overall vision of the project and the needs of the target user group. The design goal can be to improve the functionality of the product, improve the user experience, reduce production costs, or launch a competitive new product on the market. For example, in the design of a smartwatch, the design goals may include achieving innovation in health monitoring functions while maintaining a stylish appearance. Design. Once the design goal is clear, the next step is to conduct a user needs analysis based on this goal. Through user needs analysis, we can gain an in-depth understanding of the actual needs and expectations of the target users and ensure that the design solution can effectively meet market demand. The analysis of user needs usually involves research on market data, user feedback, and industry trends. Taking smart watches as an example, user needs may include high-precision health monitoring functions, long-lasting batteries, easy-to-operate user interfaces, and compatibility with other smart devices. These needs reflect the user's design purpose and expected results, and are also key factors that must be considered in the design solution. Next, based on user needs, the design team needs to list a list of functional requirements for the preliminary design solution. This list lists in detail The design plan must have various functions, and the specific requirements of each function are clarified. For example, the functional requirements list of a smart watch may include: heart rate monitoring function, GPS positioning function, Bluetooth connection function, touch screen operation, and waterproof performance. This list not only covers user needs, but also includes the technology and resources required to achieve these needs. It is an important basis for judging the feasibility of the plan. After the functional requirements list is listed, the design team needs to make a feasibility judgment on the preliminary design plan. The purpose of feasibility judgment is to evaluate the feasibility of the design plan in terms of technology, cost, time, and resources, to ensure that the design goals and user needs can be achieved in actual operation. This process may involve the difficulty of technical implementation, materials, and other aspects. Considerations include material and production costs, project schedules, and relevant laws and regulations. For example, if the functional requirements list requires a smartwatch to have ultra-long battery life, but existing technology is difficult to support this requirement, or the cost of the required battery materials is too high, then the feasibility judgment result may show that the design solution is not feasible under current conditions. However, if the feasibility judgment result shows that the preliminary design solution is feasible, the design team will further extract the solution features. This process involves extracting representative and innovative design elements from the solution and using them as a reference for subsequent optimization and improvement. The extraction of solution features includes not only technical functions, but also design concepts, user experience, and market positioning.For example, the features of a smartwatch design may include an innovative health monitoring algorithm that can track the user's health data more accurately, or a specially designed user interface that allows users to view and operate more conveniently while exercising. The extraction of solution features is a key step because it is directly related to the subsequent optimization direction of the design solution. Through in-depth analysis and refinement of the preliminary design solution, it can be clear which features are the key to the success of the design and which parts need further improvement or enhancement. These features will provide a clear direction for subsequent design optimization, ensuring that the design solution is not only feasible at the current stage, but also can continuously improve its market competitiveness and user satisfaction in future optimization. In short, this step finally extracts representative solution features by clarifying the design goals, deeply analyzing user needs, listing the functional requirements, and making feasibility judgments. This systematic analysis process ensures that the design solution is reasonable and feasible in technology and the market, laying a solid foundation for subsequent design optimization and product development. Taking the design of smartwatches as an example, this process helps the design team identify and refine key features such as health monitoring functions, user interface design, and product appearance, so that they can be optimized and improved more targeted in subsequent development.

[0034] In a specific embodiment, cluster analysis is performed on the scheme features to obtain cluster analysis features, including: By using a preset clustering algorithm, the feature vector of the scheme features is normalized to obtain a feature vector set; Performing feature vector screening on the feature vector set by using an information gain method to obtain a screened feature vector set; Performing feature vector expansion processing on the filtered feature vector set to obtain an expanded feature vector set; Performing vector space dimensionality reduction on the extended feature vector set to obtain a reduced-dimensional feature vector set; Performing Euclidean distance calculation on the reduced dimension feature vector set to capture similarity feature vectors at multiple scales; Perform vector fusion on similarity feature vectors at multiple scales to generate a similarity feature vector; Vector feature analysis is performed on the similarity feature vector to obtain cluster analysis features.

[0035] Specifically, the purpose of this step is to perform a systematic cluster analysis on the scheme features through a series of processing and analysis, so as to extract cluster analysis features that can represent the characteristics of different design schemes, and provide strong support for further design optimization. First, before cluster analysis, the scheme features need to be normalized by a preset clustering algorithm. The purpose of this process is to unify the feature vectors of different scales and units into the same standard range to ensure that the differences between the features can be accurately reflected in subsequent calculations and analyses. For example, suppose we are analyzing different design schemes for smart watches, and their scheme features may include battery life, screen resolution, processor speed, etc. Due to the different units and magnitudes of these features, direct cluster analysis may lead to inaccurate results. Therefore, the standardization process adjusts these eigenvalues ​​to the same magnitude, thereby generating a standardized set of eigenvectors. Next, the eigenvector set is screened by the information gain method. The information gain method is a statistical screening technique that screens out the eigenvectors that are most important for cluster analysis by evaluating the contribution of each eigenvector to the target variable. For example, in smartwatch design, some features such as screen brightness may have a greater impact on user experience, while other features such as shell color may have a relatively small impact. Through the information gain method, the feature vectors that have the greatest impact on end-user needs and design goals can be effectively screened out, thereby obtaining a screened feature vector set. Then, the screened feature vector set is subjected to feature vector expansion processing. The purpose of this step is to enhance the accuracy and depth of clustering analysis by increasing the dimension and information content of the features. For example, assuming that the screened feature vector set includes battery life and processor speed, then during the expansion process, the time series or related statistical information (such as maximum, minimum, and average) of these two features can be added to the feature vector to enrich the feature information and form an extended feature vector set. After feature expansion, in order to reduce the computational complexity and improve the efficiency of clustering analysis, the extended feature vector set needs to be subjected to vector space dimensionality reduction processing. The dimensionality reduction process simplifies the feature space by retaining the dimensions that are most important to clustering analysis and removing redundant or irrelevant information. Common dimensionality reduction methods include principal component analysis (PCA) or linear discriminant analysis (LDA), which can significantly reduce the data dimension while maintaining the representativeness of the feature vector. For example, in the example of smartwatch design, through dimensionality reduction processing, only the main features related to user experience and performance may be retained, and other minor features are simplified or removed to form a reduced dimensionality feature vector set. Next, the Euclidean distance is calculated for the reduced dimensionality feature vector set. Euclidean distance is a common method to measure the similarity between different feature vectors. By calculating the distance between two vectors in space, similar feature vectors at multiple scales can be captured.For example, if two smartwatch designs are very close in battery life and processor speed, the Euclidean distance between them will be small, indicating that they have high similarity in these features. After that, vector fusion is performed on the similarity feature vectors at multiple scales. This process is to integrate the similarity information at different scales and generate a comprehensive similarity feature vector for more comprehensive clustering analysis. By fusing different similarity feature vectors, the accuracy and representativeness of the clustering results can be improved. For example, in the design of smartwatches, the fused similarity feature vector may integrate the information of multiple important features, ensuring that the final clustering results can reflect the true similarity between different design solutions. Finally, vector feature parsing is performed on the similarity feature vector to obtain the final clustering analysis features. The purpose of vector feature parsing is to extract representative clustering features by analyzing and interpreting the information in the similarity feature vector. For example, by analyzing the clustering analysis features of smartwatch design solutions, it may be found that some design solutions have common features in user experience, performance, and market acceptance, which will provide important guidance for further optimization and improvement of design solutions. Through this systematic analysis step, the design team can deeply understand the similarities and differences between different design schemes, and make more accurate design decisions based on this, ultimately ensuring the competitiveness of the product in the market.

[0036] In a specific embodiment, the cluster analysis feature is identified for improvement points by an improvement point identification algorithm to obtain an improvement point set, and the preliminary design scheme is optimized once according to the identified improvement point set to obtain a first optimized design scheme, including: Inputting the cluster analysis features into a preset improvement point identification algorithm to identify improvement points and obtain an improvement point set; Calculating the weight of the set of improvement points to obtain the priority ranking of each improvement point in the set of improvement points; Optimize the preliminary design scheme once based on the priority-ranked improvement points to obtain a preliminary optimization scheme; Constructing a corresponding objective function based on the design goal; Based on a preset Pareto optimization algorithm, multi-objective optimization is performed on the preliminary optimization scheme based on the objective function to obtain a preliminary non-dominated solution set; Based on a preset fitness function, each solution in the preliminary non-dominated solution set is analyzed and compared to obtain a Pareto frontier solution set; Based on the Pareto front solution set, an in-depth analysis is performed on the design goal conflicts existing in the preliminary optimization scheme to obtain a conflict analysis report; The preliminary optimization scheme is adjusted according to the preset constraint conditions and the conflict analysis report to obtain a first optimized design scheme.

[0037] Specifically, the improvement point identification algorithm can effectively improve the accuracy and rationality of the design scheme by identifying the cluster analysis features. First, the system will input the cluster analysis features into the preset improvement point identification algorithm, which will automatically identify the features of the preliminary design scheme, screen out the improvement points that may have optimization space, and form a set of improvement points. For example, in the preliminary design of a smartwatch, multiple aspects such as user interface layout, battery life, and health data monitoring accuracy may be involved. After cluster analysis, these features can identify potential optimization points, such as improving sensor accuracy or optimizing battery management algorithms. Next, the system performs weight calculation on the set of improvement points to determine the priority ranking of each improvement point in the overall design optimization. The core of this weight calculation is to reasonably allocate the optimization priority according to factors such as the impact size of the design goal, the difficulty of improvement, and resource constraints. For example, if it is found that screen power consumption is the main bottleneck of battery life in the design of a smartwatch, the weight calculation may reduce screen power consumption as the primary optimization task, while other aspects such as the adjustment of the strap material may be given a lower priority. Based on the priority-ranked improvement points, the system optimizes the preliminary design scheme once to obtain a preliminary optimization scheme. At this stage, the design team will focus resources on solving key issues with higher weights and make preliminary adjustments to the design. Taking smart watches as an example, this step may include optimizing the screen refresh rate through software algorithms to reduce power consumption while maintaining the visual experience, or adjusting the data collection frequency of sensors to improve the accuracy of health monitoring. After that, the system builds corresponding objective functions based on the design goals. These objective functions reflect the key performance indicators in the design, such as battery life, user experience, and production costs. In order to find the optimal solution among multiple design goals, the system uses the Pareto optimization algorithm. The algorithm obtains a preliminary non-dominated solution set by analyzing the performance of different design solutions on the objective function. These non-dominated solution sets show the trade-off relationship between different design goals. For example, when optimizing a smart watch, the Pareto non-dominated solution set may contain multiple design solutions, some of which focus on extending battery life, while others emphasize improving the smoothness of user operations. Next, based on the preset fitness function, the system conducts in-depth analysis and comparison of each solution in the preliminary non-dominated solution set, and finally selects the Pareto frontier solution set. This frontier solution set shows the design solution that performs best among all the considered factors. In smartwatch design, the Pareto frontier solution set may include multiple solutions that achieve an ideal balance in multiple dimensions, such as battery life, user experience, and health monitoring accuracy. However, in actual design, there are often conflicts between various goals. Therefore, the system conducts an in-depth analysis of the design goal conflicts in the preliminary optimization solution based on the Pareto frontier solution set and generates a conflict analysis report. This analysis report describes in detail the goal conflicts that may occur during the optimization process, such as increasing battery life may reduce screen brightness, or improving monitoring accuracy may increase power consumption.According to the conflict analysis report, the system will further adjust the preliminary optimization plan through preset constraints to obtain a more balanced design plan. In the application scenario of smartwatch design, this means finding the best compromise between battery life, display effect and user experience by fine-tuning the design details. In the end, the system forms the first optimized design plan through multiple iterations and adjustments. This optimization process shows how to effectively integrate multiple complex design goals through systematic improvement steps to improve the overall performance of the final product. In the smartwatch design scenario, this process ensures that the product performs well in all key dimensions, so as to better meet market needs, while avoiding excessive sacrifice of other performance when optimizing a certain goal.

[0038] In a specific embodiment, the market demand forecasting result is obtained by forecasting the market demand of the first optimization design scheme through a preset market demand algorithm, including: Extracting market demand features from the first optimization design solution using a preset market demand algorithm to obtain a feature set for market demand prediction; Performing time series analysis on the feature set of the market demand forecast to identify trend changes in future market demand and obtain market demand trend forecast results; Performing regression analysis on the first optimized design solution based on the market demand trend forecast result to obtain a market demand-solution feature correlation; Based on the preset Bayesian network model, the uncertainty in the market demand is inferred based on the market demand-solution feature correlation to obtain the probability distribution of demand forecast; wherein the uncertainty includes market volatility, uncertainty in consumer behavior, competitive situation, speed of technological innovation and supply chain risk; By using an error evaluation method, the market demand trend forecast result is verified and optimized based on the probability distribution of the demand forecast, so as to obtain an optimized market demand forecast result.

[0039] Specifically, the above process describes how to use a systematic method to predict market demand for the optimized design solution to ensure that the design solution can meet the demand and be competitive in the actual market. First, the market demand feature extraction is performed on the first optimized design solution through a preset market demand algorithm to obtain a feature set for market demand prediction. The core of the market demand algorithm is to extract key features that can affect market demand from the design solution. These features may include product performance indicators, price positioning, preferences of target user groups, etc. For example, in the design of a new smart watch, the market demand features may cover battery life, screen resolution, health monitoring functions, and uniqueness compared with existing products on the market. After obtaining the feature set for market demand prediction, time series analysis is performed to identify future market demand trend changes and obtain market demand trend prediction results. Time series analysis is a common prediction method that predicts future trends by analyzing past data. When applied to market demand prediction, time series analysis can reveal seasonal fluctuations in market demand, long-term growth trends, and potential market changes. For example, by performing time series analysis on the sales data of the smart watch market in the past few years, it can be predicted whether consumer demand for smart watches will increase in the future, as well as the speed and magnitude of the growth. Based on the market demand trend forecast results, the first optimized design solution is subjected to regression analysis to obtain the market demand-solution feature correlation. Regression analysis is a statistical method used to quantify the relationship between market demand characteristics and design solutions. Through regression analysis, it is possible to determine which design features have the greatest impact on market demand, and adjust the design solution accordingly to maximize market acceptance. For example, if the regression analysis shows that the health monitoring function of the smartwatch is significantly positively correlated with market demand, the design team can consider strengthening this function to increase the market appeal of the product. Next, based on the preset Bayesian network model, the uncertainty in market demand is inferred based on the market demand-solution feature correlation to obtain the probability distribution of demand forecast. The Bayesian network model is a powerful tool that can handle uncertainty factors in market demand forecasting. Market demand forecasting is usually faced with many uncertainties, such as market volatility, uncertainty in consumer behavior, changes in competitive situation, speed of technological innovation, and supply chain risks. By modeling these uncertain factors, the Bayesian network model can infer the probability distribution of market demand under different scenarios, helping the design team to better understand and respond to potential market changes. For example, in the market forecast of smart watches, the Bayesian network model can help the team predict possible changes in market demand in the case of accelerated technological innovation or supply chain disruptions, and provide a basis for design decisions. Finally, through the error evaluation method, the market demand trend forecast results are verified and optimized based on the probability distribution of demand forecast, and the optimized market demand forecast results are obtained.Error assessment methods are used to evaluate the accuracy of forecasting models. By analyzing the deviation between the forecast results and the actual market performance, the deficiencies in the model can be identified and corresponding adjustments and optimizations can be made. For example, if the forecast shows that a certain smartwatch has a high demand in the market, but the actual sales are not satisfactory, the error assessment method can help identify the parts of the forecasting model that underestimate or overestimate certain influencing factors, so as to make improvements in future market demand forecasts. Through this series of steps, the design team can effectively predict market demand and make targeted adjustments to the optimized design scheme to improve the market competitiveness of the product. This process is particularly important in a rapidly changing market environment because it not only helps the team identify the trends and characteristics of market demand, but also copes with the uncertainty in the market, ensuring that the final design scheme can meet market demand and stand out in the fierce market competition. Taking the market demand forecasting of smartwatches as an example, combining market demand algorithms, time series analysis, regression analysis, Bayesian network models and error assessment methods, the team can build a comprehensive market demand forecasting system, thereby providing a solid foundation for the successful launch of the product.

[0040] In a specific embodiment, the market demand forecast result is evaluated for value to obtain a value evaluation result, including: Through a preset revenue forecasting model, the market demand forecasting results are analyzed for revenue, and a potential revenue evaluation result is obtained; wherein the potential revenue evaluation result includes potential sales, profit margin and market share; Conduct market competitiveness analysis based on the potential revenue assessment results to obtain a competitiveness index; Conduct consumer acceptance analysis based on the competitiveness index and obtain consumer acceptance scores; Evaluate potential risk factors in the market based on consumer acceptance scores and obtain a risk assessment report; Calculate the return on investment based on the risk assessment report to obtain the return on investment; The performance of the first optimized design solution in the market life cycle is analyzed based on the return on investment to obtain a market life cycle curve; Analyze brand influence based on the market life cycle curve to obtain the brand influence index; Conduct market expansion assessment based on the brand influence index and obtain a market expansion potential report; Perform a value assessment on the market expansion potential report to obtain a value assessment result.

[0041] Specifically, the above process describes in detail how to conduct a comprehensive value assessment of the market demand forecast results through a series of precise analysis steps to ensure the success of the design solution in the actual market and its long-term commercial value. First, the market demand forecast results are analyzed for revenue through the preset revenue forecast model to obtain the potential revenue assessment results. The revenue forecast model is a core tool used to evaluate the potential revenue of the design solution in the market. It can help predict future potential sales, profit margins and market share. For example, in the design of smart watches, the revenue forecast model may predict the sales and profit margins of new smart watches in a certain period of time in the future, as well as the market share of the product by analyzing the demand characteristics of the target market, combining pricing strategies, cost structures and sales channels. In this way, the team can understand the economic potential of the design solution and ensure that it can bring considerable economic returns to the company. After obtaining the potential revenue assessment results, the market competitiveness analysis is then conducted based on these results to obtain the competitiveness index. The purpose of market competitiveness analysis is to evaluate the competitive position of the design solution in the market. By comprehensively considering the differentiated advantages of the product, market positioning and the situation of competitors, the competitiveness index can reflect the advantages and disadvantages of the design solution when facing existing competitors. For example, if a smartwatch has a unique health monitoring function that is not yet available in the market, this feature will significantly improve the product's competitiveness index, thereby gaining a favorable position in market competition. Next, a consumer acceptance analysis is conducted based on the competitiveness index to obtain a consumer acceptance score. The core of consumer acceptance analysis is to evaluate the market's acceptance of new products. This analysis obtains consumers' overall acceptance scores of products by investigating consumers' feedback on the various functions, prices, and brand awareness of the design solution. For example, through consumer surveys and market trials, it can be found whether the health monitoring function of smartwatches is truly favored by the target user group, and whether the ease of use and practicality of this function meet consumers' expectations, thereby determining the product's acceptance in the market. Based on the consumer acceptance score, an assessment of potential risk factors in the market is conducted to obtain a risk assessment report. The purpose of this step is to identify and analyze the risks that may be faced during the product launch process. These risks include fluctuations in market demand, rapid changes in technological innovation, supply chain disruptions, and competitor responses. For example, the smartwatch market is highly competitive, and if other companies suddenly launch more advanced technologies or more attractive products, this will pose a threat to the market performance of the design solution. Therefore, through risk assessment, we can provide companies with strategies to deal with these uncertainties, thereby reducing potential risks in marketing. After completing the risk assessment, we calculate the return on investment based on the risk assessment report to obtain the return on investment. The return on investment is a key indicator to measure the commercial value of the design solution, which reflects the level of return on investment for investors in product development and marketing.By comprehensively analyzing the potential benefits, market risks and investment costs of the product, the calculated return on investment can help the company evaluate whether the design is worth continuing to invest. For example, if the potential sales of smart watches are high and the profit margin is large, but accompanied by high market risks, the company can improve the return on investment by adjusting the market strategy or reducing costs to ensure the economic feasibility of the project. Next, the performance of the first optimized design in the market life cycle is analyzed based on the return on investment to obtain the market life cycle curve. The market life cycle curve describes the entire process of a product from introduction, growth, maturity to decline in the market. By analyzing the return on investment, the performance of smart watches in different stages of the market can be predicted, and the best marketing opportunities and strategy adjustment points can be identified. For example, in the market introduction stage, sales may be low, but with the deepening of market education and brand promotion, the product will enter a period of rapid growth, and it is necessary to increase marketing efforts to expand market share. After obtaining the market life cycle curve, the brand influence analysis is performed based on the curve to obtain the brand influence index. Brand influence is an important indicator of the long-term competitiveness of a product in the market. By analyzing the performance of the design in the market, combined with marketing, customer feedback and brand loyalty, the position of the brand in the minds of consumers can be evaluated. For example, if the smartwatch achieves high user satisfaction and reputation during the marketing process, this will significantly improve the brand influence index, thus laying a good foundation for the launch of new products and market expansion in the future. Finally, a market scalability assessment is conducted based on the brand influence index to obtain a market expansion potential report, and a value assessment is conducted to obtain the final value assessment result. The purpose of the market scalability assessment is to analyze whether the design solution has the potential to expand into new markets or launch new product lines. For example, if the smartwatch is successful in the current market, the market expansion potential report will assess its possibility of entering other related markets, such as the health management market, the sports monitoring market, etc., thereby providing guidance for the company's future market strategy. On this basis, through a comprehensive value assessment, the overall commercial value of the design solution can be finally determined, providing an important reference for the company's decision-making. Through this complete value assessment process, it is ensured that the design solution not only meets the current market demand, but also has long-term market competitiveness and expansion potential.

[0042] In a specific embodiment, when the value assessment result is not within a preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy, and the first optimization design scheme is optimized for a second time according to the improvement strategy to obtain a second optimization design scheme, including: Based on the value assessment result, a comparison is performed against a preset value range to obtain a deviation analysis result; When the deviation analysis result shows that the value assessment result is not within the preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy; Based on the improvement strategy, the first optimized design solution is optimized for a second time to obtain a second optimized design solution; Re-evaluate the market demand forecast result based on the second optimized design solution to obtain a new value evaluation result; Until the new value assessment result is within the preset value range.

[0043] Specifically, the above process describes how to optimize and adjust the design scheme through a systematic method when it is found that the design scheme fails to achieve the expected market value, so as to ensure that the final design scheme can be successful in the market. First, based on the value assessment results, the pre-set value range is compared to obtain the deviation analysis results. The value range here is an ideal range set by the company based on past experience and market research, which reflects the target performance of the design scheme in the market, such as expected sales, profit margin, market share, etc. If the value assessment results deviate from this range, it means that the current design scheme has problems in some aspects and may not achieve the expected market goals. For example, if the market value assessment results of a smart watch show that its potential sales are lower than the expected range, or the market competitiveness index is not ideal, then it is necessary to conduct an in-depth analysis of the design scheme to find out the specific reasons for the deviation. When the deviation analysis results show that the value assessment results are not within the pre-set value range, the first optimized design scheme will be mined for association rules to obtain an improvement strategy. Association rule mining is a data mining technology that aims to discover the potential correlation between various factors in the design scheme, thereby revealing which design features may have an adverse effect on market performance. For example, through association rule mining, the team may find that there is a strong correlation between the battery life of smart watches and consumer acceptance, and the substandard battery performance of the current design is one of the main reasons for the low market acceptance. Therefore, the improvement strategy may suggest optimizing battery technology and extending battery life to improve the market appeal of the product. Based on the improvement strategy, the team will perform secondary optimization on the first optimized design to obtain the second optimized design. The secondary optimization process is to apply the improvement strategy obtained in the previous step to the design to make targeted adjustments and improvements. For example, the design team of the smart watch may adopt more advanced battery technology to increase the battery life of the product, and optimize other related functions at the same time to ensure the improvement of overall product performance. In addition to technical improvements, secondary optimization may also include adjustments to market strategies, such as repositioning the target consumer group or adjusting the product pricing strategy to make it more in line with market demand and competitive situation. After completing the secondary optimization, based on the second optimized design, the market demand forecast results are re-evaluated to obtain new value evaluation results. The value evaluation process at this time is similar to the initial evaluation process, and the purpose is to confirm whether the design solution after secondary optimization can meet the pre-set value range. For example, after the second optimization, whether the potential sales and market share of smart watches have increased, whether the competitiveness index has improved significantly, and whether the consumer acceptance score has met expectations. Until the new value assessment result is within the pre-set value range, it means that the design solution has finally reached the ideal market performance standard after multiple rounds of optimization.At this point, the team can determine that the design has good market potential and can enter the next stage of market promotion. For example, after multiple optimizations, the design of the smartwatch may finally achieve the expected market sales and profit margins, and be sufficiently competitive in the highly competitive market. At this time, the company can confidently launch it to the market, expecting to receive good market response and economic returns. This process emphasizes the importance of continuous optimization and adjustment in product design and market strategy to ensure that the design can not only meet expectations in technology, but also be successful in the market. Through repeated evaluation and optimization, the team can promptly discover and correct deficiencies in the design, and ultimately develop a product that meets market demand and is highly competitive, thereby occupying a favorable position in the fierce market competition.

[0044] The above describes the design optimization method based on big data analysis in the embodiment of the present invention. The following describes the design optimization device based on big data analysis in the embodiment of the present invention. Figure 2 , an embodiment of the design optimization device based on big data analysis in the embodiment of the present invention includes: The acquisition module 21 is used to acquire a preliminary design scheme from a user, and extract scheme features from the preliminary design scheme to obtain scheme features; An analysis module 22 is used to perform cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption; The identification module 23 is used to identify improvement points of the cluster analysis features through an improvement point identification algorithm to obtain an improvement point set, and optimize the preliminary design scheme once according to the identified improvement point set to obtain a first optimized design scheme; The prediction module 24 is used to perform market demand prediction on the first optimized design solution by using a preset market demand algorithm to obtain a market demand prediction result; wherein the market demand prediction result includes a potential market size, expected sales volume, and a target customer group; An evaluation module 25 is used to perform a value evaluation on the market demand forecast result to obtain a value evaluation result; The improvement module 26 is used to perform association rule mining on the first optimization design scheme to obtain an improvement strategy when the value assessment result is not within a preset value range, and perform secondary optimization on the first optimization design scheme according to the improvement strategy to obtain a second optimization design scheme.

[0045] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0046] Reference Figure 3The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0047] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0048] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0049] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0050] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0051] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A design optimization method based on big data analysis, characterized in that: The following steps are involved: Obtaining a preliminary design scheme through a user, and extracting scheme features from the preliminary design scheme to obtain scheme features; Performing cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption; By using an improvement point identification algorithm, the cluster analysis feature is identified with improvement points to obtain an improvement point set, and the preliminary design scheme is optimized once according to the identified improvement point set to obtain a first optimized design scheme; Using a preset market demand algorithm, market demand forecasting is performed on the first optimized design solution to obtain a market demand forecasting result; wherein the market demand forecasting result includes potential market size, expected sales volume, and target customer groups; Performing a value assessment on the market demand forecast result to obtain a value assessment result; When the value assessment result is not within a preset value range, association rule mining is performed on the first optimized design scheme to obtain an improvement strategy, and the first optimized design scheme is secondary optimized according to the improvement strategy to obtain a second optimized design scheme.

2. The design optimization method based on big data analysis according to claim 1, characterized in that: Extracting scheme features from the preliminary design scheme to obtain scheme features includes: Obtaining the design goals of the preliminary design plan, and performing a demand analysis on users based on the design goals to obtain user needs; wherein the user needs include design purposes and expected results; Based on the user needs, list the functional requirements of the preliminary design solution; Conducting feasibility judgment on the preliminary design scheme based on the functional requirements list to obtain a feasibility judgment result; If the feasibility judgment result is that the preliminary design scheme is feasible, then scheme feature extraction is performed on the preliminary design scheme to obtain scheme features.

3. The design optimization method based on big data analysis according to claim 1, characterized in that: Perform cluster analysis on the scheme features to obtain cluster analysis features, including: By using a preset clustering algorithm, the feature vector of the scheme features is normalized to obtain a feature vector set; Performing feature vector screening on the feature vector set by using an information gain method to obtain a screened feature vector set; Performing feature vector expansion processing on the filtered feature vector set to obtain an expanded feature vector set; Performing vector space dimensionality reduction on the extended feature vector set to obtain a reduced-dimensional feature vector set; Performing Euclidean distance calculation on the reduced dimension feature vector set to capture similarity feature vectors at multiple scales; Perform vector fusion on similarity feature vectors at multiple scales to generate a similarity feature vector; Vector feature analysis is performed on the similarity feature vector to obtain cluster analysis features.

4. The design optimization method based on big data analysis according to claim 2 is characterized in that: By using an improvement point identification algorithm, the cluster analysis feature is identified with improvement points to obtain an improvement point set, and the preliminary design scheme is optimized once according to the identified improvement point set to obtain a first optimized design scheme, including: Inputting the cluster analysis features into a preset improvement point identification algorithm to identify improvement points and obtain an improvement point set; Calculating the weight of the set of improvement points to obtain the priority ranking of each improvement point in the set of improvement points; Optimize the preliminary design scheme once based on the priority-ranked improvement points to obtain a preliminary optimization scheme; Constructing a corresponding objective function based on the design goal; Based on a preset Pareto optimization algorithm, multi-objective optimization is performed on the preliminary optimization scheme based on the objective function to obtain a preliminary non-dominated solution set; Based on a preset fitness function, each solution in the preliminary non-dominated solution set is analyzed and compared to obtain a Pareto frontier solution set; Based on the Pareto front solution set, an in-depth analysis is performed on the design goal conflicts existing in the preliminary optimization scheme to obtain a conflict analysis report; The preliminary optimization scheme is adjusted according to the preset constraint conditions and the conflict analysis report to obtain a first optimized design scheme.

5. The design optimization method based on big data analysis according to claim 1, characterized in that: The market demand prediction result is obtained by performing market demand prediction on the first optimization design scheme through a preset market demand algorithm, including: Extracting market demand features from the first optimization design solution using a preset market demand algorithm to obtain a feature set for market demand prediction; Performing time series analysis on the feature set of the market demand forecast to identify trend changes in future market demand and obtain market demand trend forecast results; Performing regression analysis on the first optimized design solution based on the market demand trend forecast result to obtain a market demand-solution feature correlation; Based on the preset Bayesian network model, the uncertainty in the market demand is inferred based on the market demand-solution feature correlation to obtain the probability distribution of demand forecast; wherein the uncertainty includes market volatility, uncertainty in consumer behavior, competitive situation, speed of technological innovation and supply chain risk; By using an error evaluation method, the market demand trend forecast result is verified and optimized based on the probability distribution of the demand forecast, so as to obtain an optimized market demand forecast result.

6. The design optimization method based on big data analysis according to claim 1, characterized in that: Performing a value assessment on the market demand forecast result to obtain a value assessment result, including: Through a preset revenue forecasting model, the market demand forecasting results are analyzed for revenue, and a potential revenue evaluation result is obtained; wherein the potential revenue evaluation result includes potential sales, profit margin and market share; Conduct market competitiveness analysis based on the potential revenue assessment results to obtain a competitiveness index; Conduct consumer acceptance analysis based on the competitiveness index and obtain consumer acceptance scores; Evaluate potential risk factors in the market based on consumer acceptance scores and obtain a risk assessment report; Calculate the return on investment based on the risk assessment report to obtain the return on investment; The performance of the first optimized design solution in the market life cycle is analyzed based on the return on investment to obtain a market life cycle curve; Analyze brand influence based on the market life cycle curve to obtain the brand influence index; Conduct market expansion assessment based on the brand influence index and obtain a market expansion potential report; Perform a value assessment on the market expansion potential report to obtain a value assessment result.

7. The design optimization method based on big data analysis according to claim 1, characterized in that: When the value assessment result is not within the preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy, and the first optimization design scheme is optimized again according to the improvement strategy to obtain a second optimization design scheme, including: Based on the value assessment result, a comparison is performed against a preset value range to obtain a deviation analysis result; When the deviation analysis result shows that the value assessment result is not within the preset value range, the first optimization design scheme is mined for association rules to obtain an improvement strategy; Based on the improvement strategy, the first optimized design solution is optimized for a second time to obtain a second optimized design solution; Re-evaluate the market demand forecast result based on the second optimized design solution to obtain a new value evaluation result; Until the new value assessment result is within the preset value range.

8. A design optimization device based on big data analysis, characterized in that: include: An acquisition module is used to acquire a preliminary design scheme from a user, and extract scheme features from the preliminary design scheme to obtain scheme features; An analysis module, used for performing cluster analysis on the scheme characteristics to obtain cluster analysis characteristics; wherein the cluster analysis characteristics include cost, efficiency and energy consumption; An identification module, used to identify improvement points of the cluster analysis features through an improvement point identification algorithm to obtain an improvement point set, and optimize the preliminary design scheme once according to the identified improvement point set to obtain a first optimized design scheme; A prediction module, used to perform market demand prediction on the first optimized design solution through a preset market demand algorithm to obtain a market demand prediction result; wherein the market demand prediction result includes a potential market size, expected sales volume, and a target customer group; An evaluation module, used to perform a value evaluation on the market demand forecast result to obtain a value evaluation result; The improvement module is used to perform association rule mining on the first optimization design scheme to obtain an improvement strategy when the value assessment result is not within a preset value range, and to perform secondary optimization on the first optimization design scheme according to the improvement strategy to obtain a second optimization design scheme.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images