Product design auxiliary system and method based on big data

Abstract

The invention belongs to the technical field of product intelligent design, and particularly relates to a product design auxiliary system and method based on big data. According to the method, the potential design direction on the market is quickly identified through big data analysis and calculation, so that the design period is shortened, the design efficiency is improved, the risk of blind design is reduced based on market popularity data and similarity analysis, it is ensured that the designed product better meets the market demand, and the market competitiveness is improved. Through weight analysis of local features and overall features of a product, it is ensured that a design scheme is more comprehensive and reasonable, through support of big data, the designed product better meets the market trend and consumer demands, the market competitiveness of the product is enhanced, the design process is more scientific and data-driven by using the big data technology, and the design efficiency is improved. According to the method, the uncertainty caused by subjective judgment is reduced, the provided reference three-dimensional product data can provide valuable reference basis for subsequent detailed design and production, and the efficiency and quality of the whole product development process are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of product intelligent design, and specifically relates to a product design assistance system and method based on big data. Background Art

[0002] With the intensification of market competition and the continuous changes in consumer demand, product design plays an increasingly important role in the success of enterprises. Traditional product design methods usually rely on the experience and subjective judgment of designers, which may have great uncertainty and risks. Especially in the face of rapidly changing markets and diverse consumer demands, traditional methods are often difficult to respond and adjust quickly.

[0003] In the traditional design process, designers usually formulate design plans based on the product's shape, size, material and other characteristics, but this approach often ignores market dynamics and competitors' design directions. The key to market demand and product success often depends on whether it can keep up with market trends and meet consumers' specific needs in a timely manner. However, due to the lack of systematic analysis of market data, design plans may not accurately predict market reactions, resulting in a waste of resources and an increased risk of design failure.

[0004] In recent years, with the development of big data technology, data-driven design methods have begun to receive more and more attention and application. Big data technology can provide more accurate and scientific decision-making basis for product design by collecting and analyzing a large amount of market data, consumer feedback and information on competitive products. Through big data analysis, we can gain a deep understanding of the relationship between market trends, consumer needs and product features, so as to better predict the market performance of products in the design stage.

[0005] However, existing product design assistance methods based on big data still have some challenges. For example, big data technology cannot be effectively applied to product design, resulting in low efficiency of product design, and the design effect cannot meet the design standards, affecting the accuracy of the design. Summary of the invention

[0006] The purpose of the present invention is to provide a product design assistance method based on big data, which can combine market popularity data, design product data, feature weights and other information to provide accurate design suggestions and decision support.

[0007] The technical solution adopted by the present invention is as follows:

[0008] A product design auxiliary method based on big data, comprising:

[0009] Obtaining overall design feature information and local design feature information of the target product;

[0010] Acquire multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information;

[0011] Acquire popularity data of multiple similar products, and calculate a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product;

[0012] Determine whether the first characteristic value meets the first preset condition, and if so, obtain similar product information of the similar product corresponding to the first characteristic value that meets the first preset condition;

[0013] Acquire the design product data, and calculate the product similarity value between the design product and the similar product according to the design product data and the similar product information;

[0014] Obtaining multiple product local feature information corresponding to the similar product information, and obtaining weight values ​​according to the multiple product local feature information;

[0015] Calculate product design value based on product similarity value and weight value;

[0016] Determine whether the product design value meets the second preset condition, and if so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design;

[0017] The corresponding product design information is obtained according to the reference product design, and the reference three-dimensional product data is output.

[0018] In a preferred embodiment, the step of obtaining the overall design feature information and the local design feature information of the target product includes:

[0019] Obtain target product design feature data;

[0020] Acquire corresponding multiple target product design features according to the target product design feature data;

[0021] Obtaining target product local feature information corresponding to each target product design feature;

[0022] The overall characteristic information of the target product is obtained according to a plurality of target product design characteristics.

[0023] In a preferred embodiment, the step of obtaining the heat data of a plurality of similar products and calculating the first characteristic value between each similar product and the target product according to the heat data of each similar product and the overall design characteristic information of the target product comprises:

[0024] Get the popularity data of multiple similar products;

[0025] Obtain multiple popularity scores for each similar product based on the popularity data of each similar product;

[0026] Obtain the number of design features corresponding to the overall characteristic information of the target product;

[0027] The first feature value of each similar product and the target product is calculated based on the multiple heat scores and the number of design features of each similar product, where the calculation formula is:

[0028]

[0029] In the formula, Z represents the first eigenvalue, k represents the number of multiple heat scores for each similar product, where k = 1, 2, 3…t, J k It is represented as the k-th heat score of each similar product, and L is represented as the number of design features corresponding to the overall characteristic information of the target product.

[0030] In a preferred embodiment, the step of obtaining multiple popularity scores of each similar product according to the popularity data of each similar product includes:

[0031] Get multiple ratings from the popularity data of each similar product;

[0032] Convert multiple scores into multiple conversion scores with unified scoring requirements;

[0033] Obtain the corresponding weight coefficient based on the market attention of each conversion score;

[0034] The heat score of each similar product is calculated based on each conversion score and each weight coefficient of each similar product, where the calculation formula is:

[0035] J k =ω k ·R k ;

[0036] In the formula, J k Represents the k-th heat score of each similar product, ω k Represented as the weight coefficient of the k-th conversion score in the popularity data of each similar product, R k Represented as the k-th conversion score in the popularity data of each similar product.

[0037] In a preferred embodiment, the step of obtaining the design product data and calculating the product similarity value between the design product and the similar product according to the design product data and the similar product information includes:

[0038] Obtain design product data;

[0039] Acquire multiple product local feature vectors according to the designed product data;

[0040] Acquire multiple similar local feature vectors corresponding to multiple product local feature vectors according to similar product information;

[0041] The product similarity value between the design product and the similar product is calculated based on the product local feature vector and the similar local feature vector, where the calculation formula is:

[0042]

[0043] In the formula, X represents the product similarity value, m represents the number of multiple product local feature vectors and the number of multiple similar local feature vectors, where m = 1, 2, 3...h, A m Represented as the local feature vector of the mth product, B m Represented as the mth similar local feature vector.

[0044] In a preferred embodiment, the step of obtaining a plurality of product local feature information corresponding to the similar product information and obtaining a weight value according to the plurality of product local feature information includes:

[0045] Obtaining local feature information of multiple products corresponding to similar product information;

[0046] Obtaining a feature weight table, wherein the feature weight table includes a plurality of product features and a weight value corresponding to each local feature;

[0047] Acquire corresponding target local features according to multiple product local feature information;

[0048] Obtain the corresponding weight value from the feature weight table according to the target local features.

[0049] In a preferred embodiment, the step of calculating the product design value according to the product similarity value and the weight value includes:

[0050] The product design value is calculated based on the product similarity value and weight value, where the calculation formula is:

[0051] P = X * Q;

[0052] In the formula, P represents the product design value, X represents the product similarity value, and Q represents the weight value.

[0053] In a preferred embodiment, the step of determining whether the product design value meets the second preset condition, and if so, marking the design product corresponding to the product design value meeting the second preset condition as a reference product design, includes:

[0054] Obtaining popularity scores of multiple first similar products in similar product information;

[0055] Sort multiple product design values ​​from large to small, and mark the product with the largest design value as a similar product design value;

[0056] The product design threshold is calculated according to the number of design features corresponding to the overall characteristic information of the target product, the popularity scores of multiple first similar products and the design values ​​of similar products, wherein the calculation formula is:

[0057]

[0058] Where S represents the product design threshold, Y represents the similar product design value, L represents the number of design features corresponding to the overall feature information of the target product, and i represents the number of heat scores of multiple first similar products, where i = 1, 2, 3…n, E i It is represented as the popularity score of the i-th first similar product;

[0059] Determine whether each product design value exceeds the product design threshold;

[0060] If the product design value exceeds the product design threshold, the product design is determined to meet the comparison requirements, and the similar product corresponding to the product design value exceeding the product design threshold is marked as a reference product design;

[0061] If the product design value does not exceed the product design threshold, it is determined that the product design does not meet the comparison requirements.

[0062] The present invention also provides a product design assistance system based on big data, which is used in the above-mentioned product design assistance method based on big data, comprising:

[0063] Design feature module, used to obtain the overall design feature information and local design feature information of the target product;

[0064] A similar product module, used to obtain multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information;

[0065] A first feature module, used to obtain popularity data of multiple similar products, and calculate a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product;

[0066] A first judgment module is used to judge whether the first characteristic value meets the first preset condition, and if so, obtain similar product information of the similar product corresponding to the first characteristic value meeting the first preset condition;

[0067] A product similarity module is used to obtain design product data and calculate the product similarity value between the design product and the similar product based on the design product data and similar product information;

[0068] A weight module is used to obtain a plurality of product local feature information corresponding to the similar product information, and obtain a weight value according to the plurality of product local feature information;

[0069] Product design module, used to calculate product design value based on product similarity value and weight value;

[0070] A second judgment module is used to judge whether the product design value meets the second preset condition, and if so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design;

[0071] The reference module is used to obtain corresponding product design information according to the reference product design and output reference three-dimensional product data.

[0072] And, a product design auxiliary terminal based on big data, comprising:

[0073] one or more processors;

[0074] a storage device having one or more programs stored thereon;

[0075] When the one or more programs are executed by the one or more processors, the one or more processors implement the big data-based product design assistance method.

[0076] The technical effects achieved by the present invention are:

[0077] The present invention can quickly identify design directions with potential in the market through big data analysis and calculation, thereby shortening the design cycle and improving design efficiency. Based on market popularity data and similarity analysis, it can reduce the risk of blind design and ensure that the designed products are more in line with market demand. Through weight analysis of local and overall characteristics of products, it can ensure that the design scheme is more comprehensive and reasonable, and improve the overall design quality of products. With the support of big data, the designed products are more in line with market trends and consumer needs, and the market competitiveness of products is enhanced. The use of big data technology makes the design process more scientific and data-driven, reducing the uncertainty caused by subjective judgment. The reference three-dimensional product data provided can provide valuable reference basis for subsequent detailed design and production, and improve the efficiency and quality of the entire product development process. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 is a flow chart of the method provided by the present invention;

[0079] Figure 2 It is a system module diagram provided by the present invention. DETAILED DESCRIPTION

[0080] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0081] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0082] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0083] Secondly, the present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the convenience of explanation, the schematic diagrams are only examples and should not limit the scope of protection of the present invention.

[0084] Please refer to the attached Figure 1 As shown, a product design assistance method based on big data is provided, including:

[0085] S1. Obtaining overall design feature information and local design feature information of the target product;

[0086] S2. Acquire multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information;

[0087] S3, obtaining popularity data of multiple similar products, and calculating a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product;

[0088] S4, determining whether the first characteristic value meets the first preset condition, and if so, obtaining similar product information of a similar product corresponding to the first characteristic value meeting the first preset condition;

[0089] S5, obtaining design product data, and calculating a product similarity value between the design product and similar products based on the design product data and similar product information;

[0090] S6, obtaining local feature information of multiple products corresponding to the similar product information, and obtaining weight values ​​according to the local feature information of multiple products;

[0091] S7. Calculate the product design value according to the product similarity value and weight value;

[0092] S8. Determine whether the product design value meets the second preset condition. If so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design.

[0093] S9. Obtain corresponding product design information according to the reference product design, and output reference three-dimensional product data.

[0094] As in the above steps S1 to S9, the design feature data of the product are collected. These data may include the shape, size, material, etc. of the product. Based on these design feature data, feature set data of the product are extracted, including multiple local feature information (such as different parts of the product) and overall feature information (such as the overall appearance of the product). Based on the overall design feature information and the local design feature information, multiple similar products corresponding to the target product are collected from the market. The popularity data of similar products on the market are collected. These data may come from sales data, market surveys, social media feedback, etc. Based on these market popularity data and the overall feature information of the product, a first feature value is calculated. The calculated first feature value is compared with a preset condition. If the value meets the first preset condition, the similar product is marked as similar product information. More design product data are collected. These design product data include detailed design drawings, 3D models, and detailed structures of the design product. Based on these design product data and the similar product information marked previously, the product similarity value is calculated to evaluate the similarity between the current design and the target product design. Multiple local feature information are extracted from the similar product information. Based on these local feature information, the weight value of each feature is calculated. The weight value reflects the weight of each feature. The importance of features to product design. According to the product similarity value and weight value calculated previously, a product design value is comprehensively calculated. The calculated product design value is compared with the second preset condition. If the value meets the second preset condition, the design is marked as a reference product design, indicating that the design has reference value. According to the reference product design, the corresponding product design information is obtained. Finally, the reference three-dimensional product data is output for further design and development. Through big data analysis and calculation, the design direction with potential in the market can be quickly identified, thereby shortening the design cycle and improving design efficiency. Based on market heat data and similarity analysis, the risk of blind design is reduced, ensuring that the designed product is more in line with market demand. Through weight analysis of local and overall features of the product, the design scheme is ensured to be more comprehensive and reasonable, and the overall design quality of the product is improved. With the support of big data, the designed product is more in line with market trends and consumer needs, enhancing the market competitiveness of the product. Using big data technology, the design process is more scientific and data-driven, reducing the uncertainty caused by subjective judgment. The reference three-dimensional product data provided can provide valuable reference basis for subsequent detailed design and production, and improve the efficiency and quality of the entire product development process.

[0095] In a preferred embodiment, the step of obtaining product design feature data and obtaining product feature set data according to the product design feature data, wherein the product feature set data includes a plurality of product local feature information and product overall feature information, comprises:

[0096] S101, obtaining product design feature data;

[0097] S102, acquiring corresponding multiple product design features according to the product design feature data;

[0098] S103, obtaining product local feature information corresponding to each product design feature;

[0099] S104. Obtain overall product feature information based on multiple product design features.

[0100] As in the above steps S101 to S104, basic data related to product design are collected. These data may include the appearance, size, shape, material, function, etc. of the product. The collected design feature data are analyzed to extract the features corresponding to each design feature. For example, the design feature of a product may be "lightweight", and the corresponding features may be "material selection", "structural design", etc. Each design feature is further refined to obtain its corresponding local feature information. For example, for the "material selection" feature, the type, weight, strength and other information of the material can be obtained. For the "structural design" feature, the specific shape and size of the structure can be obtained. After comprehensive analysis of multiple design features, the corresponding local feature information can be obtained. To the overall characteristic information of the product, this step is to integrate all the local characteristic information to form a comprehensive understanding of the product as a whole. For example, by combining the information of "material selection" and "structural design", the overall weight and overall strength of the product can be obtained. By refining the product design features and obtaining detailed local characteristic information and overall characteristic information, we can have a more comprehensive understanding of the design features of the product, which is conducive to refined design and optimization. We can gradually refine the design features and extract characteristic information to ensure the accuracy and completeness of the data, reduce information omissions and errors in the design process, and design based on detailed characteristic data. We can better utilize the results of data analysis, make scientific and reasonable design decisions, and improve design quality and efficiency.

[0101] In a preferred embodiment, the step of obtaining market product popularity data and calculating the first feature value according to the market popularity data and the overall feature information of the product includes:

[0102] S301, obtaining popularity data of multiple similar products;

[0103] S302, obtaining multiple popularity scores of each similar product according to the popularity data of each similar product;

[0104] S303, obtaining the number of design features corresponding to the overall characteristic information of the target product;

[0105] S304. Calculate the first feature value of each similar product and the target product according to the multiple popularity scores and the number of design features of each similar product, wherein the calculation formula is:

[0106]

[0107] In the formula, Z represents the first eigenvalue, k represents the number of multiple heat scores for each similar product, where k = 1, 2, 3…t, J k It is represented as the k-th heat score of each similar product, and L is represented as the number of design features corresponding to the overall characteristic information of the target product.

[0108] As in the above steps S301 to S304, the popularity data of multiple products similar to the target product are obtained through market data sources (such as sales records, user feedback, social media comments, etc.). According to the popularity data of each similar product, the market performance of each similar product is converted into multiple popularity scores. These scores can be obtained based on factors such as sales volume, consumer evaluation, market share, etc., reflecting the market popularity of each similar product, and extracting the overall characteristic information of the target product, especially the number related to design features. Design features usually include product appearance, functional modules, material selection, etc. These features will affect the market performance of the product. Based on the multiple popularity scores of similar products and the number of design features of the target product, the first eigenvalue between each similar product and the target product is calculated. This eigenvalue can be regarded as a measure of the degree of matching between the market popularity of similar products and the design features of the target product. Through the popularity data of multiple similar products, designers can make design choices based on market performance, ensure that the design direction is more in line with market demand, and reduce the risk of design solutions being out of touch with the market. Combining the popularity scores of similar products with the number of design features of the target product can evaluate the market potential of the target product at an early stage, help designers optimize design solutions, and improve the market competitiveness of products.

[0109] In a preferred embodiment, the step of obtaining the popularity scores of multiple similar products according to the popularity data of multiple similar products includes:

[0110] S3021. Obtain multiple scores from the popularity data of each similar product;

[0111] S3022. Convert multiple scores into multiple conversion scores with unified scoring requirements;

[0112] S3023. Obtain corresponding weight coefficients according to the market attention of each conversion score;

[0113] S3024. Calculate each heat score of each similar product according to each conversion score of each similar product and multiple weight coefficients, where the calculation formula is:

[0114] J k =ω k ·R k ;

[0115] In the formula, J k Represents the k-th heat score of each similar product, ω k Represented as the weight coefficient of the k-th conversion score in the popularity data of each similar product, R k Represented as the k-th conversion score in the popularity data of each similar product.

[0116] As in the above steps S3021 to S3024, the popularity data of similar products usually comes from multiple item ratings. For example, the multiple item ratings include the rating of local appearance A, the rating of local appearance B, the rating of local appearance C, the rating of materials, the ratings of products by different age groups (teenagers, adults, and the elderly), etc. Each item may have a different quantification method and numerical range. These data provide multiple ratings for each similar product, but the dimensions of different ratings are inconsistent and cannot be directly compared and summed. In order to uniformly process different types of data, it is necessary to convert the ratings of different dimensions into the same rating standard. The influence of the popularity data of different items on market performance varies. For example, local A may not be important in user evaluation in some markets, but it may be important in others. In other markets, user evaluation may be a more important indicator. Therefore, a weight coefficient must be assigned to each conversion score according to the market attention of different projects. The conversion scores and corresponding weight coefficients of multiple similar products are obtained, and the heat score of each similar product is calculated. By standardizing different types of scores, the heat score can be compared and calculated more reasonably, ensuring that the results of different data sources can be quantified under the same framework. The weight coefficient is dynamically adjusted according to market attention, which can reflect the actual importance of each heat data in the market, making the heat score more in line with the actual market performance. By integrating data from multiple dimensions and performing weighted processing, the heat score can comprehensively reflect the popularity of the product in the market and avoid the deviation caused by single-dimensional data.

[0117] In a preferred embodiment, the step of determining whether the first characteristic value meets the first preset condition, and if so, obtaining similar product information of a similar product corresponding to the first characteristic value meeting the first preset condition, comprises:

[0118] S401, obtaining a feature threshold;

[0119] S402, determining whether the first characteristic value exceeds the characteristic threshold;

[0120] If the first feature value exceeds the feature threshold, it is determined that the overall heat information of similar products and the local features in the overall feature information of the product meet the similarity standard, and the product corresponding to the overall heat information of similar products exceeding the feature threshold is marked as similar product information.

[0121] As in the above steps S401 to S402, a specific feature threshold is determined. This value is used to determine whether the first feature value meets the market-recognized standard. The feature threshold can be set based on historical data, market standards or expert advice. The calculated first feature value is compared with the feature threshold. If the first feature value exceeds the feature threshold, it means that the overall market popularity information of the product and the local features in the overall feature information of the product are highly similar, that is, the similarity standard is met. This indicates that the product design is in line with market trends and has high market appeal. Products corresponding to the overall popularity information of similar products that exceed the feature threshold are marked as similar product information. These products are considered to have greater potential for success in the market and can be used as the focus of further design and development. If the first feature value is lower than the feature threshold, , indicating that the overall market popularity information of the product has a low similarity with the local features, which indicates that the design may not meet market demand or is less popular. By setting the feature threshold and judging the market potential of the product design based on the first feature value, we can accurately locate products with high market potential and optimize resource allocation and market strategies. By comparing the first feature value with the feature threshold, we can make more scientific design decisions to ensure that the selected product design has a higher probability of success in the market and reduce risks. Products marked with similar product information can receive more attention and resources, and can be further optimized and developed, thereby improving the market competitiveness and success rate of the product. By real-time monitoring and analysis of market popularity data and design features, we can quickly respond to market changes, adjust design strategies, and maintain the market competitiveness of products.

[0122] In a preferred embodiment, the step of obtaining the design product data and calculating the product similarity value between the design product and the similar product according to the design product data and the similar product information includes:

[0123] S501, obtaining design product data;

[0124] S502, obtaining multiple product local feature vectors according to the design product data;

[0125] S503, acquiring multiple similar local feature vectors corresponding to multiple product local feature vectors according to similar product information;

[0126] S504. Calculate the product similarity value between the design product and the similar product based on the product local feature vector and the similar local feature vector, wherein the calculation formula is:

[0127]

[0128] In the formula, X represents the product similarity value, m represents the number of multiple product local feature vectors and the number of multiple similar local feature vectors, where m = 1, 2, 3...h, A m Represented as the local feature vector of the mth product, B m Represented as the mth similar local feature vector.

[0129] It should be noted that the product local feature vectors correspond one-to-one to the similar local feature vectors, and the number of product local feature vectors and similar local feature vectors is equal. For example, the 5th product local feature vector corresponds to the 5th similar local feature vector.

[0130] As in the above steps S501 to S504, data related to the current product design are collected, including detailed design information, technical parameters, material specifications, etc. of the product. These data constitute the basis of product design. Multiple local features are extracted from the design product data, and these local features are converted into feature vectors. The local feature vectors may include a quantitative description of each part of the product, such as different components, materials, functions, etc. Corresponding local features are extracted from similar product information, and these features are converted into similar local feature vectors. These target feature vectors represent the local feature information of the target product, which are used to compare with the local features of the current product. A suitable similarity calculation method is used to compare the product local feature vector with the similar local feature vector, and a product similarity value is calculated. This value reflects the similarity between the current product design and the target product design in local features. By calculating the product similarity value, the similarity between the current design and the target product can be accurately evaluated, helping the design team understand whether the specific direction of the design is consistent with the successful designs already on the market. The result of calculating the similarity value provides a quantitative basis for the design team, and targeted design improvements and optimizations can be made based on these data to improve the market adaptability of the design. By analyzing the similarity with the target product, the design features of successful products can be used to design products with higher market competitiveness and improve market acceptance. Based on the calculated similarity value, resources can be concentrated on designs with high similarity to the target product to avoid wasting resources on designs with low similarity, thereby improving development efficiency. Through similarity value analysis, the potential performance and acceptance of the current design in the market can be understood in advance, which is helpful for early market forecasting and strategy adjustment.

[0131] In a preferred embodiment, the step of obtaining a plurality of product local feature information corresponding to the similar product information and obtaining a weight value according to the plurality of product local feature information includes:

[0132] S601, obtaining local feature information of multiple products corresponding to similar product information;

[0133] S602: Obtain a feature weight table, wherein the feature weight table includes a plurality of product features and a weight value corresponding to each local feature;

[0134] S603, acquiring corresponding target local features according to the local feature information of multiple products;

[0135] S604: Obtain corresponding weight values ​​from a feature weight table according to the target local features.

[0136] As in the above steps S601 to S604, a plurality of local feature data are extracted from the information of the target product. These data describe the characteristics of the target product in each local part, such as material type, design specifications, functional characteristics, etc. A feature weight table is prepared. This table contains multiple product features and their corresponding weight values. The weight value indicates the importance of each feature in the overall design and is usually set based on historical data, expert evaluation or market demand analysis. The target product information and the feature weight table are compared, and the local features of the target product are matched with the features in the weight table to obtain the target local features that match the target product. The weight values ​​that match the target local features are extracted from the feature weight table. These weight values ​​reflect the importance or influence of the target product on these local features. Through the feature weight table, the importance of each local feature in the overall design can be clarified, helping the design team understand which features are crucial to the success of the product. After obtaining the weight values, the design can be optimized according to the importance of each feature, giving priority to and improving those features with higher weight values, thereby improving the market competitiveness of the product. Determining the weight values ​​of each local feature can better adjust the product design to make it more in line with market demand and user expectations, thereby improving market acceptance.

[0137] In a preferred embodiment, the step of calculating the product design value according to the product similarity value and the weight value includes:

[0138] S701. Calculate the product design value according to the product similarity value and the weight value, wherein the calculation formula is:

[0139] P = X * Q;

[0140] In the formula, P represents the product design value, X represents the product similarity value, and Q represents the weight value.

[0141] As in the above step S701, a comprehensive product design value is calculated by combining the product similarity value and the weight value. The product design value provides a quantitative evaluation index for comprehensively evaluating the pros and cons and market potential of product design. Through the calculated product design value, the design team can make more scientific decisions based on data to ensure that the design plan is more in line with market demand and target requirements. The design value comprehensively considers the similarity between the product and the target product and the importance of the features, helping the design team to design products that are more in line with market demand and user expectations, and enhancing the market adaptability of the product. According to the calculated product design value, resources can be reasonably allocated and concentrated on features with high design values, thereby improving resource utilization efficiency and the overall design effect.

[0142] In a preferred embodiment, the step of determining whether the product design value meets the second preset condition, and if so, marking the design product corresponding to the product design value meeting the second preset condition as a reference product design, comprises:

[0143] S801, obtaining popularity scores of multiple first similar products in similar product information;

[0144] S802, sorting the multiple product design values ​​from large to small, obtaining the product with the largest design value and marking it as a similar product design value;

[0145] S803, calculating a product design threshold according to the number of design features corresponding to the overall feature information of the target product, the popularity scores of multiple first similar products, and the design values ​​of similar products, wherein the calculation formula is:

[0146]

[0147] Where S represents the product design threshold, Y represents the similar product design value, L represents the number of design features corresponding to the overall feature information of the target product, and i represents the number of heat scores of multiple first similar products, where i = 1, 2, 3…n, E i It is represented as the popularity score of the i-th first similar product;

[0148] S804, determining whether each product design value exceeds a product design threshold;

[0149] If the product design value exceeds the product design threshold, the product design is determined to meet the comparison requirements, and the similar product corresponding to the product design value exceeding the product design threshold is marked as a reference product design;

[0150] If the product design value does not exceed the product design threshold, it is determined that the product design does not meet the comparison requirements.

[0151] As in the above steps S801 to S804, multiple first similar product popularity scores are extracted from the similar product information, all calculated product design values ​​are sorted, and the maximum value, i.e., the similar product design value, is found. The number of design features corresponding to the overall feature information of the target product, the first similar product popularity score and the similar product design value are used to calculate a product design threshold. The product design threshold is a critical value used to determine whether the design value meets the preset standard. The design value of the current product is compared with the calculated product design threshold. If the product design value exceeds the product design threshold, it indicates that the design has high potential in terms of market popularity and feature importance, and can be marked as a reference product design. The design value has high market adaptability and competitiveness. If the product design If the value does not exceed the threshold, it means that the design has failed to meet the expected standards or market demand and cannot be used as a reference design. By setting and calculating the design threshold, a clear quantitative standard is provided to evaluate the market potential and compliance of the design, helping the team to make scientific design decisions. The calculated product design threshold provides a clear comparison standard for the design team, ensuring that only designs that meet high standards are marked as reference designs, improving the quality and reliability of the design. The selection of reference product designs is based on market popularity and the importance of features, ensuring that the final product is more in line with market demand and improving the market acceptance and success rate of the product. Products marked as reference designs can obtain more resource support, thereby focusing on these high-potential designs and improving resource utilization efficiency and development effects.

[0152] Please refer to the attached Figure 2 As shown, the present invention also provides a product design assistance system based on big data, which is used for the above-mentioned product design assistance method based on big data, including:

[0153] Design feature module, used to obtain the overall design feature information and local design feature information of the target product;

[0154] A similar product module, used to obtain multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information;

[0155] A first feature module, used to obtain popularity data of multiple similar products, and calculate a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product;

[0156] A first judgment module is used to judge whether the first characteristic value meets the first preset condition, and if so, obtain similar product information of the similar product corresponding to the first characteristic value meeting the first preset condition;

[0157] A product similarity module is used to obtain design product data and calculate the product similarity value between the design product and the similar product based on the design product data and similar product information;

[0158] A weight module is used to obtain a plurality of product local feature information corresponding to the similar product information, and obtain a weight value according to the plurality of product local feature information;

[0159] Product design module, used to calculate product design value based on product similarity value and weight value;

[0160] A second judgment module is used to judge whether the product design value meets the second preset condition, and if so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design;

[0161] The reference module is used to obtain corresponding product design information according to the reference product design and output reference three-dimensional product data.

[0162] As described above, the design feature module obtains product design feature data, and obtains product feature set data based on these data, including multiple product local feature information and overall feature information. The similar product module obtains multiple similar products corresponding to the target product. The first feature module obtains market popularity data and calculates a first feature value, which is combined with the overall feature information of the product to evaluate the market potential of the product. The first judgment module determines whether the first feature value meets the first preset condition. If so, the product is marked as similar product information. The product similarity module obtains design product data and calculates the product similarity value based on these data and similar product information. The weight module obtains multiple local features in the similar product information, and obtains weight values ​​from the feature weight table based on these features. The product design module calculates a comprehensive product design value based on the product similarity value and the weight value. The second judgment module compares the calculated product design value with the preset condition. If the condition is met, it is marked as A reference product design indicates that the design has high market potential and competitiveness. The reference module extracts detailed information of the reference design and generates three-dimensional model data to provide a specific design basis for further product development and production. Through systematic analysis and calculation modules, the product design can be comprehensively evaluated and optimized to improve the quality and market adaptability of the design. According to market potential and design similarity, resources can be effectively allocated to the most promising designs to improve resource utilization efficiency and development effects. By calculating and judging the market popularity and design value of the product, products that better meet market demand can be designed to improve the market competitiveness and acceptance of the product. Each module provides scientific decision-making support based on data analysis and calculation, reduces the uncertainty caused by subjective judgment, and improves the accuracy and reliability of decision-making. By providing three-dimensional product data and detailed design information, the system supports the complete development process from design to production to ensure the continuity and consistency of product development.

[0163] And, a product design auxiliary terminal based on big data, comprising:

[0164] one or more processors;

[0165] a storage device having one or more programs stored thereon;

[0166] When the one or more programs are executed by the one or more processors, the one or more processors implement the big data-based product design assistance method.

[0167] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A product design assistance method based on big data, characterized in that: include: Obtaining overall design feature information and local design feature information of the target product; Acquire multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information; Acquire popularity data of multiple similar products, and calculate a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product; Determine whether the first characteristic value meets the first preset condition, and if so, obtain similar product information of the similar product corresponding to the first characteristic value that meets the first preset condition; Acquire the design product data, and calculate the product similarity value between the design product and the similar product according to the design product data and the similar product information; Obtaining multiple product local feature information corresponding to the similar product information, and obtaining weight values ​​according to the multiple product local feature information; Calculate product design value based on product similarity value and weight value; Determine whether the product design value meets the second preset condition, and if so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design; The corresponding product design information is obtained according to the reference product design, and the reference three-dimensional product data is output.

2. The product design assistance method based on big data according to claim 1 is characterized in that: The step of obtaining the overall design feature information and the local design feature information of the target product includes: Obtain target product design feature data; Acquire corresponding multiple target product design features according to the target product design feature data; Obtaining target product local feature information corresponding to each target product design feature; The overall characteristic information of the target product is obtained according to a plurality of target product design characteristics.

3. The product design assistance method based on big data according to claim 1 is characterized in that: The step of obtaining the popularity data of a plurality of similar products and calculating the first characteristic value between each similar product and the target product according to the popularity data of each similar product and the overall design characteristic information of the target product includes: Get the popularity data of multiple similar products; Obtain multiple popularity scores for each similar product based on the popularity data of each similar product; Obtain the number of design features corresponding to the overall characteristic information of the target product; The first feature value of each similar product and the target product is calculated based on the multiple heat scores and the number of design features of each similar product, where the calculation formula is: In the formula, Z represents the first eigenvalue, k represents the number of multiple heat scores for each similar product, where k = 1, 2, 3…t, J k It is represented as the k-th heat score of each similar product, and L is represented as the number of design features corresponding to the overall characteristic information of the target product.

4. The product design assistance method based on big data according to claim 1 is characterized in that: The step of obtaining multiple popularity scores of each similar product according to the popularity data of each similar product includes: Get multiple ratings from the popularity data of each similar product; Convert multiple scores into multiple conversion scores with unified scoring requirements; Obtain the corresponding weight coefficient based on the market attention of each conversion score; The heat score of each similar product is calculated based on each conversion score and each weight coefficient of each similar product, where the calculation formula is: J k =ω k ·R k ; In the formula, J k Represents the k-th heat score of each similar product, ω k Represented as the weight coefficient of the k-th conversion score in the popularity data of each similar product, R k Represented as the k-th conversion score in the popularity data of each similar product.

5. The product design assistance method based on big data according to claim 1 is characterized in that: The step of obtaining the design product data and calculating the product similarity value between the design product and the similar product according to the design product data and the similar product information includes: Obtain design product data; Acquire multiple product local feature vectors according to the designed product data; Acquire multiple similar local feature vectors corresponding to multiple product local feature vectors according to similar product information; The product similarity value between the design product and the similar product is calculated based on the product local feature vector and the similar local feature vector, where the calculation formula is: In the formula, X represents the product similarity value, m represents the number of multiple product local feature vectors and the number of multiple similar local feature vectors, where m = 1, 2, 3...h, A m Represented as the local feature vector of the mth product, B m Represented as the mth similar local feature vector.

6. The product design assistance method based on big data according to claim 1 is characterized in that: The step of obtaining a plurality of product local feature information corresponding to the similar product information and obtaining a weight value according to the plurality of product local feature information comprises: Obtaining local feature information of multiple products corresponding to similar product information; Obtaining a feature weight table, wherein the feature weight table includes a plurality of product features and a weight value corresponding to each local feature; Acquire corresponding target local features according to multiple product local feature information; Obtain the corresponding weight value from the feature weight table according to the target local features.

7. The product design assistance method based on big data according to claim 1 is characterized in that: The step of calculating the product design value according to the product similarity value and the weight value comprises: The product design value is calculated based on the product similarity value and weight value, where the calculation formula is: P = X * Q; In the formula, P represents the product design value, X represents the product similarity value, and Q represents the weight value.

8. The product design assistance method based on big data according to claim 1 is characterized in that: The step of determining whether the product design value meets the second preset condition, and if so, marking the design product corresponding to the product design value meeting the second preset condition as a reference product design, comprises: Obtaining popularity scores of multiple first similar products in similar product information; Sort multiple product design values ​​from large to small, and mark the product with the largest design value as a similar product design value; The product design threshold is calculated according to the number of design features corresponding to the overall characteristic information of the target product, the popularity scores of multiple first similar products and the design values ​​of similar products, wherein the calculation formula is: Where S represents the product design threshold, Y represents the similar product design value, L represents the number of design features corresponding to the overall feature information of the target product, and i represents the number of heat scores of multiple first similar products, where i = 1, 2, 3…n, E i It is represented as the popularity score of the i-th first similar product; Determine whether each product design value exceeds the product design threshold; If the product design value exceeds the product design threshold, the product design is determined to meet the comparison requirements, and the similar product corresponding to the product design value exceeding the product design threshold is marked as a reference product design; If the product design value does not exceed the product design threshold, it is determined that the product design does not meet the comparison requirements.

9. A product design assistance system based on big data, applied to the product design assistance method based on big data according to any one of claims 1 to 8, characterized in that: include: Design feature module, used to obtain the overall design feature information and local design feature information of the target product; A similar product module, used to obtain multiple similar products corresponding to the target product according to the overall design feature information and the local design feature information; A first feature module, used to obtain popularity data of multiple similar products, and calculate a first feature value between each similar product and the target product according to the popularity data of each similar product and the overall design feature information of the target product; A first judgment module is used to judge whether the first characteristic value meets the first preset condition, and if so, obtain similar product information of the similar product corresponding to the first characteristic value meeting the first preset condition; A product similarity module is used to obtain design product data and calculate the product similarity value between the design product and the similar product based on the design product data and similar product information; A weight module is used to obtain a plurality of product local feature information corresponding to the similar product information, and obtain a weight value according to the plurality of product local feature information; Product design module, used to calculate product design value based on product similarity value and weight value; A second judgment module is used to judge whether the product design value meets the second preset condition, and if so, mark the design product corresponding to the product design value meeting the second preset condition as a reference product design; The reference module is used to obtain corresponding product design information according to the reference product design and output reference three-dimensional product data.

10. A product design auxiliary terminal based on big data, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the big data-based product design assistance method as described in any one of claims 1 to 8.

Images