Decision-making method and system for ship cabin design scheme, medium and terminal

Abstract

According to the decision-making method for the ship cabin design scheme, firstly, influence parameters of ship cabin design are collected and input, wherein the influence parameters at least comprise humanized demand parameters and personalized parameters; and then constructing a dual-reference grey correlation projection-TOPSIS decision model based on subjective and objective weight optimization so as to carry out quantitative decision analysis on the plurality of candidate design schemes based on the influence parameters. All the candidate design schemes are sorted according to the decision analysis result, and a sorting result, evaluation details of all the candidate design schemes and weight distribution information are visually output. And finally, selecting a finally implemented ship cabin design scheme according to a sorting result, evaluation details of each candidate design scheme and weight distribution information. A comprehensive and detailed decision analysis method can be provided for a ship cabin design scheme, and efficient utilization of ship cabin design resources is achieved.

Description

Technical Field

[0001] This invention belongs to the field of ship design technology, specifically relating to a decision-making method, system, medium, and terminal for ship cabin design schemes. Background Technology

[0002] In today's rapidly developing maritime era, ships, as the core tools for humankind to explore and utilize the ocean, are undergoing a profound transformation in their design and construction philosophy, shifting from a "machine-centric" to a "human-centric" approach. Against this backdrop, the concept of "human-machine-environment" systems engineering has become crucial for ensuring crew efficiency, physical and mental health, navigational safety, and the smooth operation of overall maritime missions. This concept emphasizes an organic whole: "human" refers to the crew, the operators and core service recipients of the system; "machine" refers to the ship's various equipment, control systems, and cabin layout; and "environment" includes both physical (such as temperature, lighting, noise, and vibration) and psychological (such as feelings of spatial oppression and social isolation). An excellent "human-machine-environment" system pursues efficient, safe, and comfortable interaction and collaboration among these three elements, ultimately achieving the goal of "the ship is suitable for the people," rather than "people adapt to the ship."

[0003] However, despite the consensus reached in the concept, existing ship cabin design still faces two bottlenecks in practice that urgently need to be addressed, severely restricting the achievement of the aforementioned goals. First, the analysis of ship user needs is insufficient and lacks depth. User needs analysis is the logical starting point for any product development, and for ships with complex structures and limited space, it is the cornerstone directly affecting the rationality of their overall layout and long-term operational stability. However, current design processes often fail to comprehensively and accurately capture the true and deep-seated needs of shipboard users. This stems from the diversity of the user group: from the shipowner's functional and economic requirements, to the differences in living habits among crew members of different nationalities, cultures, and religious beliefs, and to the individualized characteristics of individuals in terms of age, body type, personality, and cognitive style. These needs are often implicit, vague, and dynamically changing. Traditional methods relying on questionnaires and interviews are prone to information distortion or omission, resulting in a significant gap between the final design and the user's true expectations. Second, the design decision-making process lacks objective and scientific quantitative basis. In traditional ship cabin design, despite established design specifications and guidelines, the final selection and optimization of solutions still largely rely on the personal experience and subjective judgment of the design team and review experts. Designers typically use their accumulated experience to "rationally" arrange various equipment and living facilities within a limited space to meet basic functions. However, this evaluation model, which depends on "feelings" and "conventions," is inevitably influenced by personal preferences, limitations of past projects, and preconceived notions. For example, regarding soft indicators such as "comfort," "convenience," and "psychological feelings," the lack of unified quantitative standards and data analysis support may lead to drastically different evaluations from different experts. This makes it difficult to use a precise and credible decision to judge the absolute merits and relative rankings of a ship cabin design. This lack of scientific rigor may not only bury the optimal solution but also fail to provide clear and traceable directions for improvement in design iterations. Summary of the Invention

[0004] In view of the problems existing in the prior art described above, this application provides a decision-making method, system, medium and terminal for ship cabin design schemes, which can provide a comprehensive and detailed decision analysis method for ship cabin design schemes and realize the efficient utilization of ship cabin design resources.

[0005] To achieve the above and other related objectives, the present invention provides a method for making decisions on ship compartment design schemes, comprising the following steps:

[0006] Collect and input the impact parameters of ship cabin design, including at least human-centered requirements parameters and personalized parameters;

[0007] A dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed to conduct quantitative decision analysis on multiple candidate design schemes based on influence parameters.

[0008] Based on the decision analysis results, all candidate design schemes are ranked in order of merit, and the ranking results, evaluation details of each candidate design scheme, and weight allocation information are visualized and output.

[0009] Based on the ranking results, evaluation details of each candidate design scheme, and weight allocation information, the final ship cabin design scheme to be implemented was selected.

[0010] Optionally, human-centered parameters include shipowner requirements, social values, cultural differences, ethnicity, design style preferences, and nationality; personalized parameters include individual characteristics and personality traits.

[0011] Optionally, parameters influencing the design of ship compartments can be collected and entered, including:

[0012] Perform data cleaning, integration, and coding on both quantitative and qualitative parameters.

[0013] Optionally, a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed to perform quantitative decision analysis on multiple candidate design schemes based on influence parameters, including:

[0014] The set of influencing parameters is standardized to eliminate the influence of dimensions;

[0015] Calculate the combined subjective and objective weights of the influencing parameters;

[0016] Determine the ideal and negative ideal solutions of candidate design schemes;

[0017] Calculate the grey relational projection values ​​of each candidate design scheme relative to the ideal solution;

[0018] Calculate the TOPSIS relative similarity of each candidate design scheme;

[0019] The weighted fusion grey relational projection value is compared with the TOPSIS value to obtain the comprehensive decision value used for ranking each candidate design scheme.

[0020] Optionally, the set of influencing parameters is standardized to eliminate the influence of dimensions, including:

[0021] Based on the attributes of the influencing parameters, they are divided into four categories: benefit-type, cost-type, fixed-type, and interval-type. Corresponding normalization functions are then applied to each category to transform them into extremely large parameters with values ​​in the interval (0, 1).

[0022] Benefit-oriented parameters (higher is better): ;

[0023] Cost parameters (lower is better): ;

[0024] Fixed parameters (the closer to a certain fixed value y0j, the better): ;

[0025] Interval parameters (preferably falling within the interval [yminj, ymaxj]):

[0026] ;

[0027] Where i, k = 1, 2, ..., n (scheme index); j = 1, 2, ..., m (parameter index);

[0028] Standardized decision matrix: .

[0029] Optionally, the combined subjective and objective weights of the influencing parameters are calculated, including:

[0030] Using AHP to determine subjective weights This includes constructing the judgment matrix, performing column normalization, summing by row, and calculating the weight vector;

[0031] Using the entropy weight method to confirm objective weights This includes constructing the original decision matrix, the normalized judgment matrix, calculating the information entropy value, and calculating the entropy weight;

[0032] The subjective weights obtained by the AHP method are obtained using a multiplicative ensemble approach. Objective weights obtained by the entropy weight method The components are merged to form a comprehensive weight W, calculated using the following formula:

[0033] .

[0034] Optionally, the ideal and negative ideal solutions of the candidate design schemes are determined, including:

[0035] Construct a weighted normalized decision matrix C = (c ij ) m×n , where c ij =w i ×e ij ; i=1, 2,..., m; j=1, 2,..., n;

[0036] Let the ideal solution be C. + The value of the j-th attribute is Let the ideal solution be C. － The value of the j-th attribute is ;

[0037] The ideal solution is: ;

[0038] The negative ideal solution is: .

[0039] Optionally, the grey relational projection values ​​of each candidate design scheme relative to the ideal solution are calculated, including:

[0040] Calculate the grey relational coefficients between each alternative solution and the ideal solution and the negative ideal solution;

[0041] Based on the grey relational coefficient, establish the ideal grey relational judgment matrix F. + With the negative ideal grey relational judgment matrix F － ;

[0042] Based on the grey relational coefficient and the comprehensive weight W, calculate the ideal-optimal weighted grey relational judgment matrix M. + and the negative ideal-worst weighted grey relational matrix M － The formula is as follows:

[0043] ;

[0044] ;

[0045] The formula for calculating the grey relational projection weights is as follows:

[0046] ;

[0047] The grey relational projection values ​​of the ideal solution and the negative ideal solution are as follows:

[0048] ; ;

[0049] in A larger value indicates that the solution is closer to the ideal solution; A larger value indicates that the solution is closer to the negative ideal solution;

[0050] Establish a ranking rule for the solutions, if and (And at least one strict inequality holds), then scheme A t Better than A z ;

[0051] like and (And at least one strict inequality holds), then scheme A t With A z No difference;

[0052] like and or and Then the preference coefficient method is used for correction:

[0053] ;

[0054] Here, α and β are preference coefficients, which reflect the decision-maker's degree of preference and concern for the projection values ​​of alternatives and ideal solutions, and alternatives and negative ideal solutions, respectively. α < β, α + β = 1.

[0055] Another aspect of the present invention provides a decision-making system for ship cabin design schemes, comprising:

[0056] The parameter input module is used to collect and input the parameters affecting the design of ship cabins. These parameters include at least human-centered design parameters and personalized design parameters.

[0057] The parameter modeling and analysis module is used to construct a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization, so as to perform quantitative decision analysis on multiple candidate design schemes based on influence parameters.

[0058] The results output module is used to rank all candidate design schemes based on the decision analysis results and visualize the ranking results, evaluation details of each candidate design scheme and weight allocation information.

[0059] The scheme selection module is used to select the final ship cabin design scheme to be implemented based on the ranking results, the evaluation details of each candidate design scheme, and the weight allocation information.

[0060] In another aspect, the present invention provides a storage medium storing a computer program that, when executed by a processor, implements the decision-making method for the ship compartment design scheme described above.

[0061] Another aspect of the present invention provides a terminal, comprising:

[0062] Memory, used to store computer programs;

[0063] A processor is used to execute computer programs stored in memory so that the terminal executes the decision-making method for the ship compartment design scheme described above.

[0064] As described above, the decision-making method, system, medium, and terminal for ship compartment design provided by the present invention have at least the following beneficial technical effects:

[0065] The decision-making method for ship cabin design schemes of this invention first collects and inputs the influencing parameters of ship cabin design, including at least human-centered requirements parameters and personalized parameters. Then, a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed to perform quantitative decision analysis on multiple candidate design schemes based on the influencing parameters. Next, based on the decision analysis results, all candidate design schemes are ranked in order of merit, and the ranking results, evaluation details of each candidate design scheme, and weight allocation information are visualized and output. Finally, based on the ranking results, evaluation details of each candidate design scheme, and weight allocation information, the final ship cabin design scheme to be implemented is selected. This method provides a comprehensive and detailed decision analysis method for ship cabin design schemes, enabling efficient utilization of ship cabin design resources.

[0066] The decision-making method and system for ship cabin design schemes of this invention integrates human factors engineering, design science, and computer science to construct an evaluation system covering at least 25 human factors parameters. Based on big data technology, it achieves data integration and cross-departmental sharing, providing a comprehensive data foundation for decision-making. It breaks through the bottleneck of user profile construction in traditional ship design, accurately predicting and quantifying multi-dimensional user needs, ensuring that the design scheme closely aligns with users' true expectations. By introducing a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization, it combines qualitative and quantitative analysis, outputting accurate quantitative ranking results, fundamentally guaranteeing the scientific and objective nature of the design scheme evaluation. Attached Figure Description

[0067] Figure 1 The diagram shows a flowchart of a decision-making method for ship cabin design schemes provided in an embodiment of the present invention.

[0068] Figure 2 The diagram shows a module schematic of the decision-making system for a ship cabin design scheme provided in Embodiment 2 of the present invention.

[0069] Figure 3 The diagram shown is a structural schematic of the terminal provided in Embodiment 4 of the present invention. Detailed Implementation

[0070] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention.

[0071] It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of the present invention. Although the illustrations only show components related to the present invention and are not drawn according to the actual number, shape and size of the components, the shape, quantity, positional relationship and proportion of each component can be arbitrarily changed under the premise of realizing the technical solution of this invention, and the layout of the components may also be more complex.

[0072] Example 1

[0073] This embodiment provides a decision-making method for ship cabin design schemes, referring to... Figure 1 This includes the following steps:

[0074] S100: Collect and input the impact parameters of ship cabin design, including at least human-centered requirements parameters and personalized parameters;

[0075] As shown in Table 1, the human-centered design parameters include shipowner requirements, social values, cultural differences, ethnicity, design style preferences, and nationality. Personalized parameters include individual characteristics and personality traits. The total number of influencing parameters is no less than 25. Based on this, data cleaning, integration, and coding are performed on both quantitative and qualitative parameters to achieve efficient data analysis and decision support. Specifically, for quantitative parameters, parameter cleaning is first performed: parameters irrelevant to the human factors design of ship cabins are removed; for data with missing values, methods such as mean imputation, median imputation, or mode substitution are used to complete the data; outliers are detected based on Z-score normalization or interquartile range (IQR) mechanisms, and removal, correction, or retention operations are performed as appropriate. Then, parameter organization is performed: feature screening is conducted through correlation analysis, and parameters with significant impact on cabin design are selected to form a feature subset. Finally, coding is performed: the structured coding and storage of numerical parameters are completed. For qualitative parameters, the process begins with parameter cleaning: standardizing the representation format of non-numerical data, such as converting text descriptions into standardized labels or categorical variables; filtering out irrelevant content and ambiguous expressions; and using methods like label encoding and one-hot encoding to transform qualitative information into quantitative representations. Next, parameter processing is performed: applying Natural Language Processing (NLP) techniques, such as Latent Dirichlet Allocation (LDA) topic modeling, to extract key themes from text parameters such as user needs; and conducting sentiment analysis on user feedback to achieve a quantitative assessment of satisfaction. Finally, encoding is completed: the structured encoding and storage of the quantified data are finished.

[0076]

[0077] S200: Construct a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization to perform quantitative decision analysis on multiple candidate design schemes based on the aforementioned influence parameters;

[0078] To scientifically solve the multi-scheme evaluation problem, a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed. Using user satisfaction and design efficiency as comprehensive evaluation criteria, candidate design schemes are modeled and solved, including the following steps:

[0079] S201: Standardize the set of influencing parameters to eliminate the influence of dimensions;

[0080] Specifically, the influencing parameters are first input into the dual-benchmark grey relational projection-TOPSIS decision model.

[0081] To eliminate the "incommensurability" caused by inconsistencies in the dimensions and numerical scales of evaluation parameters, the original impact parameter values ​​in the decision matrix need to be standardized to establish a mapping function from actual measured values ​​to dimensionless evaluation values. Based on the attributes of the impact parameters, they are classified into four categories: benefit-type, cost-type, fixed-type, and interval-type. Corresponding normalization functions are then applied to each category to uniformly transform them into extremely large parameters with values ​​in the interval (0, 1).

[0082] Benefit-oriented parameters (higher is better): ;

[0083] Cost parameters (lower is better): ;

[0084] Fixed parameter (the closer to a certain fixed value y) 0j (Superior type) ;

[0085] Interval type parameter (falling into the interval [y minj， y maxj (Preferred type)

[0086] ;

[0087] Where i,k=1,2,……n (scheme index); j=1,2,……m (parameter index);

[0088] Standardized decision matrix: .

[0089] S202: Calculate the combined subjective and objective weights of the influencing parameters;

[0090] To balance the subjective value of expert experience with the objective information of the data itself during the decision-making process, a combined subjective and objective weighting method is adopted, integrating the Analytic Hierarchy Process (AHP) and the entropy weighting method. This method first uses AHP to obtain the subjective weights reflecting expert judgment. Then, the entropy weight method is used to mine the objective weights implied by the discreteness of the data. Finally, the subjective and objective weights are integrated to obtain the comprehensive weight W, which reflects both decision preferences and the inherent structure of the data.

[0091] (1) Using AHP to determine subjective weights First, based on the hierarchical structure, elements belonging to the same upper-level criterion are compared pairwise to construct a judgment matrix. This matrix uses a 1-9 scale to quantify the relative importance of each factor, thus systematically reflecting the experts' judgments on the importance of the indicators. The specific calculation steps are as follows:

[0092] a. Construct the judgment matrix

[0093] Let the set of objects participating in the evaluation be... The parameter set is Evaluation object M i For D j The value is denoted as x ij (i=1, 2, ..., m; j=1, 2, ..., n), then the resulting judgment matrix X is: .

[0094] b. Column normalization processing

[0095] Normalize the judgment matrix X column by column to obtain the matrix: .

[0096] c. Sum by row

[0097] Add the normalized matrices of each column of the judgment matrix row by row: , i=1,2……m.

[0098] d. Calculate the weight vector

[0099] vector Normalization yields the subjective weights of each indicator. i=1,2……m, and finally the subjective weights are obtained. for .

[0100] (2) Using the entropy weight method to confirm objective weights ,

[0101] Entropy weight method determines objective weights based on the dispersion of evaluation index data. The smaller the degree of variation of an indicator, the less information it reflects, and the lower its corresponding weight. The specific calculation steps are as follows:

[0102] a. Constructing the original decision matrix

[0103] Let the set of objects participating in the evaluation be... The parameter set is Evaluation object M i For D j The value is denoted as x ij (i=1, 2, ..., m; j=1, 2, ..., n), then the resulting judgment matrix X is: .

[0104] b. Normalized judgment matrix

[0105] To eliminate the influence of dimensions, the original matrix is ​​normalized by range, resulting in a standardized matrix V = (V ij ) m×n ;

[0106] For efficiency-related indicators (the larger the better): ;

[0107] For cost-related indicators (the smaller the better): ;

[0108] Where max(x) j ) and min(x j ) are the maximum and minimum values ​​of the j-th index in all schemes, respectively.

[0109] Convert the standardized values ​​into probabilistic form and calculate the feature weight of the i-th scheme under the j-th indicator:

[0110] .

[0111] c. Calculate the information entropy value

[0112] The information entropy e of the j-th indicator j Defined as:

[0113] .

[0114] d. Calculate entropy weights

[0115] Define the difference coefficient d j =1-e j The larger the value, the stronger the discriminative power of the indicator in the evaluation, and the higher its weight should be assigned. Therefore, the entropy weight of the j-th indicator is:

[0116] ;

[0117] (3) Determination of the combined subjective and objective weights

[0118] To balance the complementary information of expert judgment and the inherent distribution of data, a multiplicative ensemble method is used to adjust the subjective weights obtained by the AHP method. Objective weights obtained by the entropy weight method The components are then merged to form a comprehensive weight W, calculated as follows:

[0119] ;

[0120] Among them, W has a comprehensive weight. Subjective weighting, For objective weighting.

[0121] S203: Determine the ideal and negative ideal solutions of the candidate design schemes;

[0122] Ideal solution C + With negative ideal solution C － Let A be a virtual reference scheme constructed based on the evaluation scheme set A, representing the globally optimal and globally worst levels in terms of evaluation indicators, respectively. The specific determination process is as follows:

[0123] (1) Constructing a weighted normalized decision matrix

[0124] Based on the standardized decision matrix R = (e) obtained from the aforementioned steps ij ) m×n With the comprehensive weight vector W=[w1,w2,……,w n Construct the weighted normalization matrix C = (c ij ) m×n , where c ij =w i ×e ij ;i=1,2,…,m; j=1,2,…,n.

[0125] (2) Determine the ideal solution and the negative ideal solution

[0126] Let the ideal solution be C. + The value of the j-th attribute is Let the ideal solution be C. － The value of the j-th attribute is The following criteria are determined based on the indicator type:

[0127] Ideal solution: ;

[0128] Negative ideal solution: .

[0129] S204: Calculate the grey relational projection value of each candidate design scheme relative to the ideal solution;

[0130] To evaluate the proximity of alternative solutions to an ideal reference point from a geometric perspective, a grey relational projection method is introduced. This method uses the ideal solution C... + With negative ideal solution C － The reference sequence is used as the reference sequence, and each alternative solution is used as the comparison sequence. The merits of the solutions are judged by calculating the grey relational coefficient and vector projection value.

[0131] (1) Calculation of grey relational coefficient

[0132] Calculate the grey relational coefficients between each alternative solution and the ideal solution and the negative ideal solution:

[0133] ;

[0134] ;

[0135] Where ρ∈[0,1], ρ is usually taken to be ≤0.5 to maintain good discriminative power.

[0136] (2) Construction of Grey Relational Judgment Matrix

[0137] Based on the grey relational coefficient, establish the ideal grey relational judgment matrix F. + With the negative ideal grey relational judgment matrix F － :

[0138] ;

[0139] .

[0140] (3) Weighted grey relational matrix

[0141] Based on the grey relational coefficient and comprehensive weight W, the ideal-optimal weighted grey relational judgment matrix M + And the negative ideal-worst weighted grey relational matrix M － for:

[0142] ;

[0143] .

[0144] (4) Calculation of grey relational projection values

[0145] If each decision option is considered as a vector, then each decision option A is called a vector. i With reference vector A * The included angle The central angle is the gray-relational projection angle, and its cosine value is... Let decision option A be... i The modulus is d i Then decision plan A i In benchmark scheme A *The projection value on the surface is called the gray relational projection value D. i .

[0146] The ideal gray relational projection value is:

[0147] ;

[0148] The negative ideal-grey relational projection value is:

[0149] ;

[0150] The weights of the grey relational projection obtained by synthesizing and rearranging the above formula are:

[0151] ;

[0152] The grey relational projection values ​​of the ideal solution and the negative ideal solution are:

[0153] ; ;

[0154] in A larger value indicates that the solution is closer to the ideal solution; A larger value indicates that the solution is closer to the negative ideal solution.

[0155] (5) Scheme ranking rules

[0156] The following decision rule is established based on the projected values:

[0157] like and (And at least one strict inequality holds), then scheme A t Better than A z ;

[0158] like and (And at least one strict inequality holds), then scheme A t With A z No difference;

[0159] like and or and Then the preference coefficient method is used for correction:

[0160]

[0161] Here, α and β are preference coefficients, which reflect the decision-maker's degree of preference and concern for the projection values ​​of alternatives and ideal solutions, and alternatives and negative ideal solutions, respectively. Generally, α < β, and α + β = 1.

[0162] When concerned about how closely the alternative solutions resemble the ideal solution, follow... Sort in descending order; when concerned with the degree of distance between alternative solutions and the negative ideal solution, follow... Sort in ascending order.

[0163] S205: Calculate the TOPSIS relative similarity of each candidate design scheme;

[0164] To quantify the degree of approximation between each scheme and the ideal solution in terms of spatial distance, the TOPSIS method is used to calculate the relative closeness C. i This index constructs a comprehensive evaluation scale for ranking solutions by measuring the Euclidean distance between the proposed solution and the ideal solution and the negative ideal solution. The specific calculation process is as follows:

[0165] (1) Calculate the Euclidean distance from scheme di to the ideal solution C+:

[0166] ;

[0167] (2) Calculate scheme d i To the negative ideal solution C － Euclidean distance:

[0168] ;

[0169] (3) Calculate the relative similarity of each scheme:

[0170] ;

[0171] Where, 0≤C i ≤1, C i The larger the value, the closer the solution di is to the ideal solution and the further away it is from the negative ideal solution, and the better the overall evaluation of the corresponding solution.

[0172] S206: The relative proximity between the weighted fused grey relational projection value and TOPSIS is used to obtain the comprehensive decision value for ranking each candidate design scheme.

[0173] To achieve a comprehensive evaluation of the design schemes, the performance of each scheme in terms of directional proximity (grey relational projection) and spatial proximity (TOPSIS) to the ideal reference point is considered. A weighted fusion method is used to calculate the comprehensive decision value T for each scheme, forming the final ranking basis. The specific calculation formula is as follows:

[0174] ;

[0175] Where T is the comprehensive decision value; r is the grey relational degree; C I This represents the relative proximity of TOPSIS.

[0176] S300: Based on the decision analysis results, rank all the candidate design schemes according to their merits and demerits, and visualize the ranking results, evaluation details of each candidate design scheme and weight allocation information.

[0177] A bar chart with sorting functionality is used to visualize the comprehensive decision values ​​of each option. The height of the bar chart represents the comprehensive score of the option, and users can sort the options in ascending or descending order of score by clicking the table header. This visualization method helps decision-makers quickly identify the Pareto optimal option and the score distribution characteristics of option clusters, enabling intuitive comparative analysis of the advantages and disadvantages of options.

[0178] Meanwhile, the ranking results, parameter evaluation details, and weight allocation information can be uniformly converted into CSV structured format through the data format conversion engine, and a one-click download function is provided. Users can export data from the entire decision-making process to a standard format file, ensuring lossless migration of analysis results across different platforms, while also meeting the needs for data archiving, report generation, and cross-system data exchange.

[0179] S400: Select the final ship cabin design scheme to be implemented based on the ranking results, the evaluation details of each candidate design scheme, and the weight allocation information.

[0180] Example 2

[0181] This embodiment provides a decision-making system for ship cabin design schemes, referring to... Figure 2The system comprises a parameter input module, a parameter modeling and analysis module, a result output module, and a scheme selection module. The parameter input module collects and inputs influencing parameters for ship cabin design, including at least human-centered and personalized parameters. The parameter modeling and analysis module constructs a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization to perform quantitative decision analysis on multiple candidate design schemes based on influencing parameters. The result output module ranks all candidate design schemes based on the decision analysis results and visualizes the ranking results, evaluation details of each candidate design scheme, and weight allocation information. The result output module includes a scheme information display submodule, a single parameter evaluation information submodule, a weight allocation display submodule, a scheme decision result display submodule, and a decision analysis result output submodule. These submodules display and output information about the schemes participating in the evaluation, the evaluation results of each parameter, the weight allocation information of each parameter, and the overall decision result. The scheme information display submodule uses a dynamic table format on the system's front-end page to display basic information about each design scheme, allowing for a quick overview of the scheme. The single-parameter evaluation information submodule provides independent visualization components for each parameter, including radar charts and bar charts, to display the evaluation results of each parameter in detail, helping users gain a deeper understanding of the performance of each scheme in different parameters. The weight allocation display submodule uses a visually stacked bar chart to show the weight percentage of different parameters in the overall evaluation, allowing users to clearly see the importance of each parameter in the decision-making process and easily adjust weight settings to meet specific design requirements. The decision result display submodule uses a bar chart with sorting functionality to display the decision results of each scheme, ranking the design schemes according to the comprehensive decision value to help decision-makers quickly identify the optimal and worst schemes. The decision analysis result output submodule converts the output results displayed at the front end into CSV format and triggers download, allowing users to export decision results and analysis data to common file formats for easy saving, printing, or sharing with other systems. The scheme selection module selects the final ship cabin design scheme to be implemented based on the ranking results, evaluation details of each candidate design scheme, and weight allocation information.

[0182] Example 3

[0183] This embodiment provides a storage medium storing a computer program. When executed by a processor, this program implements the decision-making method for ship cabin design schemes described in Embodiment 1. The storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0184] Example 4

[0185] This embodiment provides a terminal, such as Figure 3As shown, the terminal in this embodiment includes a memory and a processor. The memory stores computer programs. Preferably, the memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk. The processor is connected to the memory and executes the computer program stored in the memory to enable the terminal to execute the decision-making method for the ship cabin design scheme described in Embodiment 1. Preferably, the processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0186] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A decision-making method for ship cabin design schemes, characterized in that, Includes the following steps: Collect and input the influencing parameters of ship cabin design, including at least human-centered requirements parameters and personalized parameters; A dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed to perform quantitative decision analysis on multiple candidate design schemes based on the aforementioned influence parameters. Based on the decision analysis results, all candidate design schemes are ranked in order of merit, and the ranking results, evaluation details of each candidate design scheme, and weight allocation information are visualized and output. Based on the ranking results, the evaluation details of each candidate design scheme, and the weight allocation information, the final ship cabin design scheme to be implemented is selected.

2. The decision-making method for ship cabin design schemes according to claim 1, characterized in that, Human-centered parameters include shipowner requirements, social values, cultural differences, race, design style preferences, and nationality; personalized parameters include individual characteristics and personality traits.

3. The decision-making method for ship cabin design schemes according to claim 1, characterized in that, Collect and input the impact parameters of ship compartment design, including: Perform data cleaning, integration, and coding on both quantitative and qualitative parameters.

4. The decision-making method for ship cabin design schemes according to claim 1, characterized in that, A dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization is constructed to perform quantitative decision analysis on multiple candidate design schemes based on the aforementioned influence parameters, including: The set of influencing parameters is standardized to eliminate the influence of dimensions; Calculate the combined subjective and objective weights of the influencing parameters; Determine the ideal and negative ideal solutions of the candidate design schemes; Calculate the grey relational projection value of each candidate design scheme relative to the ideal solution; Calculate the TOPSIS relative similarity of each of the candidate design schemes; The grey relational projection value and the TOPSIS are weighted and fused to obtain a comprehensive decision value for ranking each candidate design scheme.

5. The decision-making method for ship cabin design schemes according to claim 4, characterized in that, The set of influencing parameters is standardized to eliminate the influence of dimensions, including: Based on the attributes of the influencing parameters, they are divided into four categories: benefit-type, cost-type, fixed-type, and interval-type. Corresponding normalization functions are then applied to each category to transform them into extremely large parameters with values ​​in the interval (0, 1). Benefit-oriented parameters (higher is better): ; Cost parameters (lower is better): ; Fixed parameter (the closer to a certain fixed value y) 0j (Superior type) ; Interval parameters (preferably falling within the interval [yminj, ymaxj]): ； Where i, k = 1, 2, ..., n (scheme index); j = 1, 2, ..., m (parameter index); Standardized decision matrix: .

6. The decision-making method for ship cabin design schemes according to claim 5, characterized in that, Calculating the combined subjective and objective weights of the influencing parameters includes: Using AHP to determine subjective weights This includes constructing the judgment matrix, performing column normalization, summing by row, and calculating the weight vector; Using the entropy weight method to confirm objective weights This includes constructing the original decision matrix, the normalized judgment matrix, calculating the information entropy value, and calculating the entropy weight; The subjective weights obtained by the AHP method are obtained using a multiplicative ensemble approach. Objective weights obtained by the entropy weight method The components are merged to form a comprehensive weight W, calculated using the following formula: 。 7. The decision-making method for ship cabin design schemes according to claim 6, characterized in that, Determine the ideal and negative ideal solutions of the candidate design schemes, including: Construct a weighted normalized decision matrix C = ( cij ) m×n , where c ij =w i ×e ij ; i=1, 2,..., m; j=1, 2,..., n; Let the ideal solution be C. + The value of the j-th attribute is Let the ideal solution be C. － The value of the j-th attribute is ; The ideal solution is: ; The negative ideal solution is: .

8. The decision-making method for ship cabin design schemes according to claim 7, characterized in that, Calculate the grey relational projection values ​​of each candidate design scheme relative to the ideal solution, including: Calculate the grey relational coefficients between each alternative solution and the ideal solution and the negative ideal solution; Based on the grey relational coefficient, establish the ideal grey relational judgment matrix F. + With the negative ideal grey relational judgment matrix F － ; Based on the grey relational coefficient and the comprehensive weight W, calculate the ideal-optimal weighted grey relational judgment matrix M. + and the negative ideal-worst weighted grey relational matrix M － The formula is as follows: ； ； The formula for calculating the grey relational projection weights is as follows: ； The grey relational projection values ​​of the ideal solution and the negative ideal solution are as follows: ； ； in A larger value indicates that the solution is closer to the ideal solution; A larger value indicates that the solution is closer to the negative ideal solution; Establish a ranking rule for the solutions, if and (And at least one strict inequality holds), then scheme A t Better than A z ; like and (And at least one strict inequality holds), then scheme A t With A z No difference; like and or and Then the preference coefficient method is used for correction: ； Here, α and β are preference coefficients, which reflect the decision-maker's degree of preference and concern for the projection values ​​of alternatives and ideal solutions, and alternatives and negative ideal solutions, respectively. α < β, α + β = 1.

9. A decision-making system for ship cabin design schemes, characterized in that, include: The parameter input module is used to collect and input the influence parameters of the ship's cabin design. The influence parameters include at least human-centered requirements parameters and personalized parameters. The parameter modeling and analysis module is used to construct a dual-benchmark grey relational projection-TOPSIS decision model based on subjective and objective weight optimization, so as to perform quantitative decision analysis on multiple candidate design schemes based on the influence parameters. The results output module is used to rank all the candidate design schemes based on the decision analysis results, and to visualize the ranking results, evaluation details of each candidate design scheme and weight allocation information. The scheme selection module is used to select the final ship cabin design scheme to be implemented based on the sorting results, the evaluation details of each candidate design scheme, and the weight allocation information.

10. A storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the decision-making method for the ship cabin design scheme as described in any one of claims 1 to 8.

11. A terminal, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute a computer program stored in the memory, so that the terminal executes the decision-making method for the ship cabin design scheme according to any one of claims 1 to 8.

Images