Packaging structure simulation analysis and regulation system and method based on multi-objective optimization

Abstract

The application belongs to the technical field of packaging design, and provides a packaging structure simulation analysis and regulation system and method based on multi-objective optimization. The method comprises the following steps: obtaining fuzzy constraint information and clear constraint information from design requirement information input by a user; automatically generating a plurality of first packaging structure design schemes based on the fuzzy constraint information, performing simulation analysis on the first packaging structure design schemes with optimization difficulty analysis as the target, and determining the first packaging structure design scheme with the lowest optimization difficulty as a second packaging structure design scheme; and obtaining a third packaging structure design scheme based on the second packaging structure design scheme and the clear constraint information. The application generates an adaptive scheme based on fuzzy constraints, screens a low optimization difficulty scheme, and then combines clear constraints for accurate optimization, which not only solves the problems of requirement conversion and constraint loss, but also balances multi-dimensional targets, reduces scheme modification and resource waste, and significantly improves design efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of packaging design, in particular to a packaging structure simulation analysis and regulation system and method based on multi-objective optimization. BACKGROUND

[0002] With the promotion of digitalization and intelligentization, the field of packaging design is undergoing profound changes. Currently, various online design platforms and AI design tools are emerging, providing users with a variety of packaging box design solutions. For example, some online design platforms support users to complete packaging box design independently through template dragging, parameter adjustment, etc.; other platforms use artificial intelligence technology to automatically generate design drawings according to user needs, greatly shortening the design cycle and reducing the design threshold. However, these innovative technologies still face significant defects in practical application.

[0003] However, in the process of existing AI generating packaging box design drawings, there is a common problem of lack of demand transformation and constraint mechanism. Most platforms only take the explicit parameter-type requirements input by users as a single guide, failing to transform abstract functional requirements (such as load-bearing, moisture-proof, portability), style preferences (such as minimalist style, national trend style), and use scenarios (such as e-commerce transportation, gift giving) into explicit and executable constraint conditions. This extensive generation mode leads to a serious disconnection between the AI output design drawings and user expectations, such as designing high-end gift packaging into cartoon style, or generating structures that cannot meet the actual transportation protection requirements, causing repeated modification of design schemes and waste of resources.

[0004] From the perspective of technical implementation, existing AI design tools have significant deficiencies in the construction and execution of constraint mechanisms. On the one hand, some platforms lack fine-grained control over the AI generation process, failing to accurately map user requirements into model-recognizable technical parameters and visual rules, leaving the AI generation behavior in a "borderless" state; on the other hand, even a few platforms that introduce constraints are mostly limited to simple style or size restrictions, making it difficult to balance multiple dimensions such as functionality, cost, and environmental protection. For example, in the trade-off between lightweight and protection performance, AI may generate overly simplified structures due to lack of effective constraints, leading to product damage during transportation; or in the application of environmentally friendly materials, the generated design drawings cannot match the process requirements of recyclable materials due to the lack of explicit material property constraints.

[0005] In summary, there is an urgent need for an accurate and efficient packaging structure design solution in the existing technology. SUMMARY

[0006] To this end, the present application provides a packaging structure simulation analysis and regulation method and system based on multi-objective optimization, an electronic device, a computer storage medium, and a computer program product to solve at least one of the above technical problems.

[0007] In a first aspect, the application provides a packaging structure simulation analysis and regulation method based on multi-objective optimization, comprising the following method steps:

[0008] Fuzzy constraint information and clear constraint information are respectively extracted from user input design requirement information; the fuzzy constraint information and the clear constraint information each include multiple design target information;

[0009] Based on the fuzzy constraint information, a plurality of first packaging structure design schemes are automatically generated, simulation analysis is performed on each first packaging structure design scheme with optimization difficulty analysis as the target, and the first packaging structure design scheme with the lowest optimization difficulty is determined as a second packaging structure design scheme;

[0010] Based on the second packaging structure design scheme, a third packaging structure design scheme is obtained by optimization based on the clear constraint information.

[0011] In a second aspect, the application provides a packaging structure simulation analysis and regulation system based on multi-objective optimization, the system comprising an extraction unit, a scheme generation unit and a scheme optimization unit;

[0012] The extraction unit extracts fuzzy constraint information and clear constraint information from user input design requirement information; the fuzzy constraint information and the clear constraint information each include multiple design target information;

[0013] The scheme generation unit automatically generates a plurality of first packaging structure design schemes based on the fuzzy constraint information, performs simulation analysis on each first packaging structure design scheme with optimization difficulty analysis as the target, and determines the first packaging structure design scheme with the lowest optimization difficulty as a second packaging structure design scheme;

[0014] The scheme optimization unit obtains a third packaging structure design scheme by optimization based on the clear constraint information, based on the second packaging structure design scheme.

[0015] In a third aspect, the application provides an electronic device, comprising at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program is executed by the processor to implement the method according to any one of the preceding aspects.

[0016] In a fourth aspect, the application provides a computer storage medium storing a computer program executable by a processor to implement the method according to any one of the preceding aspects.

[0017] In a fifth aspect, the present application provides a computer program product comprising a computer program executable by a processor to implement the method of any one of the preceding aspects.

[0018] The present application generates and optimizes the scheme in stages by separating the fuzzy and clear constraints: first, generate an adaptive scheme based on fuzzy constraints and screen low optimization difficulty schemes, and then combine the clear constraints for accurate optimization. In this way, the demand conversion and constraint missing problems are solved, and the multi-dimensional target is balanced, which can reduce scheme modification and resource waste, and significantly improve design efficiency and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0020] Figure 1 is a flowchart of a packaging structure simulation analysis and regulation method based on multi-objective optimization disclosed by the embodiments of the present application;

[0021] Figure 2 is a structure diagram of a generative adversarial network disclosed by the embodiments of the present application;

[0022] Figure 3 is a structure diagram of a packaging structure simulation analysis and regulation system based on multi-objective optimization disclosed by the embodiments of the present application. DETAILED DESCRIPTION

[0023] The embodiments of the present application will be described below by specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the specification. Obviously, the described embodiments are part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0024] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0025] As Figure 1 shown, the embodiments of the present application disclose a packaging structure simulation analysis and regulation method based on multi-objective optimization, comprising the following method steps:

[0026] S10, obtain fuzzy constraint information and clear constraint information from the design requirement information input by the user; the fuzzy constraint information and the clear constraint information each include a plurality of design target information.

[0027] The design requirement information input by the user usually contains multi-dimensional targets, such as requirements for the protection performance (such as compression strength, impact resistance) of the packaging, cost control (such as material usage, processing complexity), environmental friendliness (such as the proportion of recyclable materials, degradation rate), appearance style (such as minimalist style, retro style), and the like. Among these requirements, some can be directly quantified as specific parameters, and some are expressed in an abstract manner.

[0028] Among them, the clear constraint information refers to design targets that can be defined by specific numerical values or explicit standards, such as "packaging load ≥ 5 kg", "material cost ≤ 2 yuan per piece", "size is 20 cm × 15 cm × 10 cm", and the like. Such information has clear boundaries and verifiability. The fuzzy constraint information refers to design targets that are difficult to quantify directly and rely on subjective judgment, such as "packaging needs to reflect high-end feel", "structure should be easy for the elderly to operate", "overall style is coordinated and unified", and the like. Such information needs to be converted into executable design parameters through subsequent processing.

[0029] Through structured analysis of user requirements, the above two types of constraint information are extracted, and each type of constraint information includes a plurality of interrelated design targets (such as clear constraints that may include load, size, cost, and the like, and fuzzy constraints that may include style, ease of use, brand recognition, and the like).

[0030] S20, automatically generate a plurality of first packaging structure design schemes based on the fuzzy constraint information, and perform simulation analysis on each first packaging structure design scheme with optimization difficulty as the target to determine the first packaging structure design scheme with the lowest optimization difficulty as the second packaging structure design scheme.

[0031] First, based on the fuzzy constraint information extracted in S10, a plurality of first packaging structure design schemes are automatically generated using generative AI or parametric design tools. These packaging structure design schemes need to meet the targets in the fuzzy constraints, such as generating different structure schemes using gilding process and matte materials for "high-end feel" requirements, and generating a variety of layout schemes with easy-to-tear openings and carrying straps for "ease of use" requirements. During the generation process, constraint rule library is introduced (such as mapping "high-end feel" to "color saturation ≤ 30%, process includes more than one surface treatment"), to ensure that the scheme conforms to the overall orientation of the fuzzy constraints.

[0032] Subsequently, simulation analysis is performed on each first packaging structure design scheme with optimization difficulty as the target. Optimization difficulty is mainly evaluated through the following dimensions:

[0033] Adjustability of structural parameters: whether the adjustment of parameters such as material thickness, corner radius, etc. will trigger a chain reaction;

[0034] Degree of multi-objective conflict: whether the cost will increase significantly when the protection performance is improved, and the trade-off difficulty between the two;

[0035] Process feasibility: whether the design scheme is suitable for the existing production line, and the complexity of modifying the process.

[0036] The above dimensions are quantitatively scored by simulation tools, and finally the first packaging structure design scheme with the lowest optimization difficulty (i.e. high structural adjustability, small target conflict, and strong process adaptability) is determined as the second packaging structure design scheme, so as to reduce the resource consumption in the subsequent optimization process and improve the design efficiency.

[0037] S30, based on the second packaging structure design scheme, the third packaging structure design scheme is obtained by optimization based on the clear constraint information.

[0038] For the second packaging structure design scheme with lower optimization difficulty, the clear constraint information extracted in S10 is used as a hard index to perform multi-objective optimization on the scheme. For example, if the clear constraints include "material cost ≤ 2 yuan", "compression strength ≥ 50N", and "recyclable material ratio ≥ 80%", the optimization is performed as follows:

[0039] Adjust structural parameters: such as reducing the material thickness of non-bearing areas and increasing the reinforcing ribs of key parts;

[0040] Replace the material combination: such as using a "kraft paper + honeycomb core" composite structure to improve the strength while keeping the cost;

[0041] Optimize process details: such as changing the full-wrapping design to local splicing to reduce processing cost while meeting the recycling requirements.

[0042] In the optimization process, a multi-objective optimization algorithm (such as genetic algorithm, particle swarm algorithm) is used to solve the clear constraint targets cooperatively, so as to meet the individual target while avoiding the performance loss of other targets. Finally, a third packaging structure design scheme that meets all the quantitative standards of the clear constraint information is generated, realizing the balance of packaging structure in multiple dimensions such as function, cost, and process.

[0043] The present application generates and optimizes the scheme in stages by separating the fuzzy and clear constraints: first, generate an adaptive scheme based on fuzzy constraints and select a low-optimization-difficulty scheme, and then combine the clear constraints for precise optimization. This setting not only solves the problem of demand conversion and constraint loss, but also balances multi-dimensional targets, reduces scheme modification and resource waste, and significantly improves design efficiency and accuracy.

[0044] Optionally, the design requirement information input by the user is respectively extracted to obtain fuzzy constraint information and clear constraint information, including:

[0045] The natural language processing model is used for semantic analysis of the design requirement information input by the user, and quantitative indicators and non-quantitative descriptions contained therein are extracted;

[0046] Each of the quantitative indicators is determined as clear constraint information, and the quantitative indicators at least include packaging size, bearing parameter, material cost threshold, and recyclable material proportion, which are directly verifiable numerical targets;

[0047] Each of the non-quantitative descriptions is determined as fuzzy constraint information, and the non-quantitative descriptions at least include style preference, operation convenience, and visual coordination, which are abstract targets depending on subjective judgment.

[0048] First, a pre-trained natural language processing model (such as a BERT model) is used for semantic analysis of the text requirement input by the user, and two types of information are extracted from the requirement through word segmentation, entity recognition, and relationship extraction: one type is a quantitative indicator containing a specific numerical value (such as “packaging size 20 cm x 15 cm x 10 cm”, “bearing ≥ 5 kg”), and the other type is a non-quantitative description without an explicit numerical value (such as “style simple and atmospheric”, “convenient for children to open”).

[0049] Second, the extracted information is classified: all quantitative indicators are classified into clear constraint information, and this type of information has clear verification standards, such as “material cost ≤ 2 yuan per unit”, “recyclable material proportion ≥ 80%”, etc., which can be directly used as hard parameters for subsequent optimization.

[0050] At the same time, non-quantitative descriptions are classified into fuzzy constraint information, which depends on subjective judgment, such as “overall visual coordination”, “reflecting high-end texture”, etc., which need to be mapped to executable design parameters (such as “color contrast ≤ 40%”, “including gold stamping process”) through a subsequent rule library.

[0051] Finally, the two types of constraint information are aggregated respectively to form a constraint set containing multiple design targets, providing a structured input for subsequent scheme generation.

[0052] Optionally, the fuzzy constraint information is used to automatically generate a plurality of first packaging structure design schemes, including:

[0053] The fuzzy constraint information is mapped to an executable design parameter combination through a pre-set constraint rule library, and the constraint rule library includes associated visual design rules belonging to style preference type constraints, associated structure feature rules belonging to function experience type constraints, and associated identification layout rules belonging to brand identification type constraints;

[0054] Generative adversarial networks are used, with the design parameter combinations as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints;

[0055] The initial design scheme set is subjected to feasibility filtering to eliminate schemes that violate basic physical rules and process standards, resulting in several first packaging structure design schemes.

[0056] First, the abstract fuzzy constraint information is transformed into specific design parameters using a pre-defined constraint rule base. This rule base contains at least the following three types of mapping rules:

[0057] Related visual design rules (style preference constraints): For example, mapping "high-end feel" to "color saturation ≤30%, use of hot stamping / UV process, sans-serif font ratio ≥80%";

[0058] Related structural feature rules (functional experience constraints): For example, mapping "easy for the elderly to operate" to "tear-off width ≥ 5mm, opening force ≤ 20N, corner radius ≥ 3mm";

[0059] Related logo layout rules (brand identification constraints): For example, mapping "highlight brand logo" to "logo area ≥ 15%, centered / top position, use brand standard colors".

[0060] The above mapping operation can solve the problem of fuzzy constraints being difficult to quantify, provide executable parameter boundaries for AI generation, and ensure that the design direction conforms to the user's intention.

[0061] Then, using a GAN architecture, such as Figure 2 As shown, the mapped design parameter combination is used as a condition input. Through adversarial training between the generator and the discriminator, a 3D packaging structure model that meets the constraints is generated. For example, inputting the parameter combination of "high-end feel + portability", the generator outputs a matte packaging box with magnetic closure and carrying handle. By adjusting the parameter weights (such as "high-end feel" weight 0.8 and "cost control" weight 0.6), a balance of multiple objectives is achieved.

[0062] Furthermore, by introducing random noise (Latent Space) and parameter perturbations, multiple design variants under the same constraints can be generated, ensuring the diversity of the initial design scheme set.

[0063] In addition, to avoid generating unmanufacturable or performance-defective solutions, reduce the cost of subsequent optimization (manual or automatic optimization), and improve design efficiency, it is also necessary to perform physical rule verification and process standard verification.

[0064] Basic physical rule verification: Check whether each scheme in the initial design scheme set violates basic physical rules. For example, structural stability and material compatibility. Specifically, verify through finite element analysis whether the deformation of the packaging box under load exceeds the safety threshold (e.g., ≤5%); and ensure that the selected materials (e.g., kraft paper) can meet the strength requirements (e.g., compressive strength ≥50N).

[0065] Process standard verification: Screening solutions that meet manufacturing process requirements, such as: fold line spacing ≥ 3mm to avoid sharp angle folds that cannot be achieved by the process; distance between printing area and die-cutting edge ≥ 2mm to prevent the pattern from being cut off.

[0066] This embodiment transforms subjective requirements into objective design parameters through a rule base, overcoming the limitations of traditional AI design that relies solely on explicit numerical values. Simultaneously, by combining the creativity of GANs with the constraints of the rule base, it ensures both the diversity of initial design solutions and that the resulting initial design solutions meet the user's design requirements. Furthermore, a feasibility filtering mechanism eliminates infeasible solutions in advance, streamlining the entire process from design to production and reducing trial-and-error costs.

[0067] Optionally, the use of a generative adversarial network, with the design parameter combination as conditional input, generates a diverse set of initial design schemes that satisfy fuzzy constraints, including:

[0068] The generator of the generative adversarial network receives the combination of design parameters as conditional input, and introduces dynamic random noise; wherein, the variance of the dynamic random noise is dynamically adjusted according to the degree of abstraction of the fuzzy constraint information;

[0069] A parameter perturbation module is set in the intermediate layer of the generator to randomly fine-tune the parameters of the design elements; the fine-tuning range is dynamically allocated based on the priority of each fuzzy constraint information.

[0070] The generated scheme is double-checked by the discriminator, including checking whether it meets the fuzzy constraints and checking the feature difference between the schemes. When the difference is lower than the preset threshold, it is fed back to the generator to increase the random noise variance or the parameter fine-tuning range.

[0071] Iterate the above process until a preset number of schemes are generated, forming a diverse set of initial design schemes.

[0072] When generating the initial design scheme set, it is necessary to generate richer variant schemes for abstract constraints. For example, for the "high-end feel," multiple implementation paths such as matte, hot stamping, and embossing should be generated simultaneously to avoid getting stuck in a single local optimum. Specifically:

[0073] In the generator of a Generative Adversarial Network (GAN), the combination of design parameters is used as a conditional input, while Gaussian random noise is introduced. Among them, noise variance The degree of abstraction of the fuzzy constraints is dynamically determined, and the noise variance is... It is positively correlated with the level of abstraction. Specifically, the higher the level of abstraction, the lower the noise variance. The larger it is, the smaller it is.

[0074] The quantification of the level of abstraction can be achieved through three-level semantic parsing, specifically:

[0075] (1) Use NLP models to segment and tag fuzzy constrained text, and extract core components such as nouns, verbs, and adjectives. For example, for “simple style and easy to open with one hand”, extract the keywords “simple style” and “easy to open with one hand”, and the modifier “easy”.

[0076] (2) Calculate the following two quantitative indicators:

[0077] Keyword abstraction level: The semantic distance between keywords and entity words (such as "size" and "material") is calculated using a pre-trained word vector model (such as Word2Vec). The greater the distance, the higher the abstraction level (e.g., "high-end feel" is 0.82 away from the entity word, and "rounded corner design" is 0.35 away).

[0078] Modifier density: The ratio of modifiers (adjectives, adverbs) to keywords (e.g., modifiers account for 100% in "high-end quality" and 50% in "slightly rounded corners").

[0079] (3) The two indicators are weighted and summed (e.g., each with a weight of 0.5) to obtain the abstractness score (in the range of [0,1]). For example, "high-end feel" gets 0.78 and "rounded corner design" gets 0.32.

[0080] The specific examples are shown in Table 1 below:

[0081]

[0082] Simultaneously, a parameter perturbation module is set in the intermediate layer of the generator (such as after the convolutional layer) to affect the design element parameters. Perform random fine-tuning:

[0083]

[0084] in, For a uniformly distributed random vector, ;

[0085] Disturbance coefficient Constraint priority is inversely proportional to constraint priority: lower priority constraints (such as "secondary visual element") receive larger values ​​(e.g., 0.2), while higher priority constraints (such as "brand logo position") receive smaller values. Value (e.g., 0.05).

[0086] Through the above-mentioned application mechanism of dynamic random noise and parameter perturbation signal of the present invention, it is possible to explore secondary constraints more boldly while ensuring the core constraints. For example, while fixing the position of the logo, the curvature of the packaging corners can be varied within a large range.

[0087] Next, for the scheme generated by the generator, the discriminator performs two tasks simultaneously:

[0088] Constraint compliance verification: Evaluate whether the generated solution meets the fuzzy constraints (e.g., use a feature extractor to determine whether the features related to "high-end feel" meet the standards).

[0089] Difference verification: Calculate the structural similarity between the generated schemes (such as Hausdorff distance, shape descriptor difference), and trigger feedback when the similarity exceeds a threshold (such as 85%).

[0090] The feedback adjustment strategy is as follows: when the difference is insufficient, dynamically increase the variance of random noise. or parameter disturbance coefficient ,For example: ,in, For the current degree of difference, The learning rate (e.g., 0.1).

[0091] Continue iterating the above process until a preset number N solutions (e.g., 50) are generated, and the solution set satisfies: average difference ≥ preset threshold (e.g., 70%); constraint compliance rate ≥ preset threshold (e.g., 90%).

[0092] The final set of solutions is stored by clustering based on dissimilarity, for example:

[0093]

[0094] Each of the scheme clusters represents a design direction (such as minimalist style or retro style), ensuring diversity coverage.

[0095] This embodiment dynamically adjusts the search strategy based on the level of abstraction and priority of constraints, solving the problem of insufficient diversity in traditional GANs under multiple constraints. Simultaneously, through a dual-validation feedback loop, it evaluates both constraint compliance and solution diversity, ensuring that the generated solutions meet requirements while avoiding duplication, thereby improving design efficiency.

[0096] Optionally, the simulation analysis of each of the first packaging structure design schemes, with the goal of optimizing the difficulty analysis, includes:

[0097] The system invokes preset multi-dimensional optimization difficulty assessment indicators and corresponding simulation analysis models; wherein, the multi-dimensional optimization difficulty assessment indicators include structural parameter adjustability indicators, multi-objective conflict degree indicators, and process adaptability indicators.

[0098] The simulation analysis model is used to process the corresponding first packaging structure design scheme to obtain the corresponding quantitative score. Based on each quantitative score, the comprehensive optimization difficulty score corresponding to the first packaging structure design scheme is calculated.

[0099] Construct an evaluation indicator system comprising three core dimensions, breaking down the optimization difficulty into quantifiable sub-indicators:

[0100] Structural parameter adjustability index: assess the degree of freedom in adjusting design parameters, such as whether adjusting material thickness will lead to a chain reaction (e.g., changes in strength require simultaneous adjustment of reinforcing ribs).

[0101] Multi-objective conflict index: quantifies the degree of contradiction between various design objectives, such as the conflict between improving protection performance (increasing material thickness) and reducing costs (reducing material usage).

[0102] Process compatibility index: Evaluate the compatibility of the design scheme with the existing production line, such as whether the folding structure is compatible with the existing die-cutting equipment.

[0103] For each of the above evaluation indicators, a dedicated simulation model is used for quantitative analysis:

[0104] Parameter sensitivity analysis model: This involves calculating the influence coefficient matrix of parameter adjustments on other parameters using finite element analysis (FEA) or parametric modeling. For example: .in, To adjust the parameters, These are the parameters that are affected. The larger the influence coefficient, the greater the adjustment. right The more significant the influence, the lower the adjustability; conversely, the less significant the influence, the higher the adjustability.

[0105] Target correlation analysis model: Calculate the Pearson correlation coefficient between targets using historical design data or Design of Experiments (DOE). .in , For different design objectives, such as cost and strength; The closer to -1, the higher the degree of conflict, and vice versa.

[0106] Process compatibility analysis model: Based on a production process knowledge base, it assesses the manufacturability of the design scheme. For example: whether the spacing between fold lines meets the minimum processing accuracy of the equipment (e.g., ≥3mm); whether the material combination is compatible with existing printing processes (e.g., the adhesion of UV inks to different materials).

[0107] The quantitative scores of each indicator are weighted and summed, resulting in a comprehensive score: ω1 × Adjustability Score + ω2 × Adjustability Conflict Score + ω3 × Process Adaptability Score. The weights of each quantitative score can be dynamically adjusted based on user priority. For example, when users emphasize "rapid production," ω3 is increased; when users emphasize "optimal performance," ω2 is increased. Understandably, the design with the lowest comprehensive score represents the first packaging structure with the lowest optimization difficulty and is thus chosen as the second packaging structure design.

[0108] This embodiment decomposes the abstract "optimization difficulty" into three quantifiable dimensions: structure, target, and process, solving the problem of traditional methods relying on subjective judgment. Moreover, the weighting of the quantitative scores can be adjusted according to the priority of user needs, making the evaluation results more in line with actual application scenarios and enhancing the relevance of the solution.

[0109] like Figure 3 As shown, this embodiment of the invention also provides a packaging structure simulation analysis and control system 10 based on multi-objective optimization, the system including an extraction unit 11, a scheme generation unit 12, and a scheme optimization unit 13;

[0110] The extraction unit 11 extracts fuzzy constraint information and clear constraint information from the design requirement information input by the user; both the fuzzy constraint information and the clear constraint information include multiple design target information.

[0111] The scheme generation unit 12 automatically generates several first packaging structure design schemes based on the fuzzy constraint information, performs simulation analysis on each first packaging structure design scheme with the goal of optimizing the difficulty, and determines the first packaging structure design scheme with the lowest optimization difficulty as the second packaging structure design scheme.

[0112] The optimization unit 13, based on the second packaging structure design scheme, optimizes and derives a third packaging structure design scheme based on the clear constraint information.

[0113] Optionally, the extraction unit 11 is used for:

[0114] Natural language processing models are used to semantically parse the design requirements information input by users, and extract the quantitative indicators and non-quantitative descriptions contained therein.

[0115] Each of the aforementioned quantitative indicators is defined as clear constraint information, and the quantitative indicators include at least directly verifiable numerical targets such as packaging size, load-bearing parameters, material cost threshold, and percentage of recyclable materials.

[0116] Each of the aforementioned non-quantitative descriptions is defined as fuzzy constraint information, and the non-quantitative descriptions include at least abstract goals that rely on subjective judgment, such as style preference, ease of operation, and visual harmony.

[0117] Optionally, the scheme generation unit 12 is used for:

[0118] The fuzzy constraint information is mapped into executable design parameter combinations through a preset constraint rule library. The constraint rule library includes associated visual design rules belonging to style preference constraints, associated structural feature rules belonging to functional experience constraints, and associated logo layout rules belonging to brand identity constraints.

[0119] Generative adversarial networks are used, with the design parameter combinations as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints;

[0120] The initial design scheme set is subjected to feasibility filtering to eliminate schemes that violate basic physical rules and process standards, resulting in several first packaging structure design schemes.

[0121] Optionally, the scheme generation unit 12 is used for:

[0122] The method employs a generative adversarial network, using the design parameter combination as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints, including:

[0123] The generator of the generative adversarial network receives the combination of design parameters as conditional input, and introduces dynamic random noise; wherein, the variance of the dynamic random noise is dynamically adjusted according to the degree of abstraction of the fuzzy constraint information;

[0124] A parameter perturbation module is set in the intermediate layer of the generator to randomly fine-tune the parameters of the design elements; the fine-tuning range is dynamically allocated based on the priority of each fuzzy constraint information.

[0125] The generated scheme is double-checked by the discriminator, including checking whether it meets the fuzzy constraints and checking the feature difference between the schemes. When the difference is lower than the preset threshold, it is fed back to the generator to increase the random noise variance or the parameter fine-tuning range.

[0126] Iterate the above process until a preset number of schemes are generated, forming a diverse set of initial design schemes.

[0127] Optionally, the scheme generation unit 12 is used for:

[0128] The system invokes preset multi-dimensional optimization difficulty assessment indicators and corresponding simulation analysis models; wherein, the multi-dimensional optimization difficulty assessment indicators include structural parameter adjustability indicators, multi-objective conflict degree indicators, and process adaptability indicators.

[0129] The simulation analysis model is used to process the corresponding first packaging structure design scheme to obtain the corresponding quantitative score. Based on each quantitative score, the comprehensive optimization difficulty score corresponding to the first packaging structure design scheme is calculated.

[0130] This invention also provides an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program, when executed by the processor, implements the method as described in any of the foregoing embodiments.

[0131] This invention also provides a computer storage medium storing a computer program that can be executed by a processor to implement the methods described in any of the foregoing claims.

[0132] This invention also provides a computer program product comprising a computer program that can be executed by a processor to implement the method as described in any of the foregoing embodiments.

[0133] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0134] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for simulation analysis and control of packaging structure based on multi-objective optimization, characterized in that: The methods and steps include the following: Fuzzy constraint information and clear constraint information are extracted from the design requirements information input by the user; both the fuzzy constraint information and the clear constraint information include multiple design target information. Based on the fuzzy constraint information, several first packaging structure design schemes are automatically generated. Simulation analysis is performed on each first packaging structure design scheme with the goal of optimizing the difficulty. The first packaging structure design scheme with the lowest optimization difficulty is determined as the second packaging structure design scheme. Based on the second packaging structure design scheme, a third packaging structure design scheme is derived by optimizing based on the clear constraint information; Fuzzy constraint information and clear constraint information are extracted from the design requirements information input by the user, including: Natural language processing models are used to semantically parse the design requirements information input by users, and extract the quantitative indicators and non-quantitative descriptions contained therein. Each of the aforementioned quantitative indicators is defined as clear constraint information, and the quantitative indicators include at least directly verifiable numerical targets such as packaging size, load-bearing parameters, material cost threshold, and percentage of recyclable materials. Each of the aforementioned non-quantitative descriptions is defined as fuzzy constraint information, and the non-quantitative descriptions include at least abstract goals that rely on subjective judgment, such as style preference, ease of operation, and visual harmony. Based on the aforementioned fuzzy constraint information, several first packaging structure design schemes are automatically generated, including: The fuzzy constraint information is mapped into executable design parameter combinations through a preset constraint rule library. The constraint rule library includes associated visual design rules belonging to style preference constraints, associated structural feature rules belonging to functional experience constraints, and associated logo layout rules belonging to brand identity constraints. Generative adversarial networks are used, with the design parameter combinations as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints; The initial design scheme set is subjected to feasibility filtering to eliminate schemes that violate basic physical rules and process standards, resulting in several first packaging structure design schemes.

2. The method for simulation analysis and control of packaging structure based on multi-objective optimization according to claim 1, characterized in that: The method employs a generative adversarial network, using the design parameter combination as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints, including: The generator of the generative adversarial network receives the combination of design parameters as conditional input, and introduces dynamic random noise; wherein, the variance of the dynamic random noise is dynamically adjusted according to the degree of abstraction of the fuzzy constraint information; A parameter perturbation module is set in the intermediate layer of the generator to randomly fine-tune the parameters of the design elements; the fine-tuning range is dynamically allocated based on the priority of each fuzzy constraint information. The generated scheme is double-checked by the discriminator, including checking whether it meets the fuzzy constraints and checking the feature difference between the schemes. When the difference is lower than the preset threshold, it is fed back to the generator to increase the random noise variance or the parameter fine-tuning range. Iterate the above process until a preset number of schemes are generated, forming a diverse set of initial design schemes.

3. The method for simulation analysis and control of packaging structure based on multi-objective optimization according to claim 2, characterized in that: Simulation analysis was performed on each of the first packaging structure design schemes with the goal of optimizing the difficulty, including: The system invokes preset multi-dimensional optimization difficulty assessment indicators and corresponding simulation analysis models; wherein, the multi-dimensional optimization difficulty assessment indicators include structural parameter adjustability indicators, multi-objective conflict degree indicators, and process adaptability indicators. The simulation analysis model is used to process the corresponding first packaging structure design scheme to obtain the corresponding quantitative score. Based on each quantitative score, the comprehensive optimization difficulty score corresponding to the first packaging structure design scheme is calculated.

4. A packaging structure simulation analysis and control system based on multi-objective optimization, characterized in that, The system includes an extraction unit, a scheme generation unit, and a scheme optimization unit; The extraction unit extracts fuzzy constraint information and clear constraint information from the design requirement information input by the user. Both the fuzzy constraint information and the clear constraint information include multiple design target information; The scheme generation unit automatically generates several first packaging structure design schemes based on the fuzzy constraint information, performs simulation analysis on each first packaging structure design scheme with the goal of optimizing the difficulty, and determines the first packaging structure design scheme with the lowest optimization difficulty as the second packaging structure design scheme. The scheme optimization unit, based on the second packaging structure design scheme, optimizes and derives a third packaging structure design scheme based on the clear constraint information; The extraction unit is used for: Natural language processing models are used to semantically parse the design requirements information input by users, and extract the quantitative indicators and non-quantitative descriptions contained therein. Each of the aforementioned quantitative indicators is defined as clear constraint information, and the quantitative indicators include at least directly verifiable numerical targets such as packaging size, load-bearing parameters, material cost threshold, and percentage of recyclable materials. Each of the aforementioned non-quantitative descriptions is defined as fuzzy constraint information, and the non-quantitative descriptions include at least abstract goals that rely on subjective judgment, such as style preference, ease of operation, and visual harmony. The scheme generation unit is used for: The fuzzy constraint information is mapped into executable design parameter combinations through a preset constraint rule library. The constraint rule library includes associated visual design rules belonging to style preference constraints, associated structural feature rules belonging to functional experience constraints, and associated logo layout rules belonging to brand identity constraints. Generative adversarial networks are used, with the design parameter combinations as input conditions, to generate a diverse set of initial design schemes that satisfy fuzzy constraints; The initial design scheme set is subjected to feasibility filtering to eliminate schemes that violate basic physical rules and process standards, resulting in several first packaging structure design schemes.

5. An electronic device, characterized in that: The electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1-3.

6. A computer storage medium, characterized in that: The computer storage medium stores a computer program that can be executed by a processor to implement the method as described in any one of claims 1-3.

7. A computer program product, characterized in that: The computer program product includes a computer program that can be executed by a processor to implement the method as described in any one of claims 1-3.

Images