Environmental design work display system

Abstract

The invention relates to the technical field of design work display, in particular to an environment design work display system, which comprises a model extraction module for scanning a design work model by adopting a three-dimensional laser scanner, acquiring point cloud data and generating a digital twinborn model; the intelligent detection module is used for detecting the digital twin model and identifying a design defect area; the dynamic optimization module is used for generating a plurality of parameter adjustment schemes for each defect area; and the interactive display module is used for synchronously displaying the original design, the optimization scheme and the key index comparison data in a side-by-side view manner, and supporting a user to select and apply the optimization scheme in real time. According to the method, the digital twin model is generated through three-dimensional laser scanning, key parameters such as the fire fighting access width and the energy-saving heat transfer coefficient are automatically detected in combination with a standard database, the defect severity score is calculated, and precision and priority ranking of problem positioning are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of design work display, and particularly relates to an environmental design work display system. BACKGROUND

[0002] In the traditional environmental design work display process, designers usually rely on two-dimensional drawings or static three-dimensional models to present the scheme. However, these methods have the following limitations:

[0003] Defect detection efficiency is low, manual inspection of whether the design conforms to fire safety, energy saving and other specifications is time-consuming and easy to miss, especially hidden problems in complex spatial structures; optimization scheme is single, adjustment of design relies on experience, lacks comprehensive evaluation of quantitative indicators, and it is difficult to balance the needs of multiple parties; the interaction is insufficient, users cannot participate in real-time scheme optimization, and the display form lacks dynamic comparison, resulting in long decision-making cycle and poor user experience.

[0004] In the prior art, digital twin technology has been applied to the field of building, but it is mostly focused on construction monitoring or operation and maintenance stage, and there is no systematic solution for automatic defect repair and multi-objective optimization in the design stage. SUMMARY

[0005] In view of the above shortcomings of the prior art, the present application provides an environmental design work display system, which can effectively solve the problems mentioned in the prior art.

[0006] To achieve the above purpose, the present application is realized by the following technical scheme:

[0007] The present application provides an environmental design work display system, comprising:

[0008] A model extraction module, which uses a three-dimensional laser scanner to scan the design work model, obtains point cloud data, and generates a digital twin model;

[0009] An intelligent detection module for detecting the digital twin model, identifying the design defect area, and calculating the defect severity score S of the defect area, setting a defect severity score threshold S T When the calculated defect severity score S is greater than the severity score threshold S T , the design work is dynamically repaired;

[0010] A dynamic optimization module generates a plurality of parameter adjustment schemes for each defect area, calculates the correction cost AC, environmental improvement value AE and user preference matching degree P of each scheme, and normalizes the correction cost AC, environmental improvement value AE and user preference matching degree P to generate a decision matrix, including correction cost score environmental improvement score user preference score The optimal scheme is obtained by synthesizing the decision matrix;

[0011] The interactive display module synchronously displays the original design, the optimization scheme and the key indicator comparison data in a side-by-side view, supports the user to select and apply the optimization scheme in real time.

[0012] Further, the intelligent detection module comprises:

[0013] The specification database unit stores design standards in a split database architecture, wherein the design standards comprise a first threshold value W and a second threshold value U, the first threshold value is a fire passage width threshold value, and the second threshold value is an energy-saving heat transfer coefficient threshold value;

[0014] The fire passage width is obtained from the digital twin model data, and the energy-saving heat transfer coefficient is obtained by the following formula:

[0015]

[0016] wherein, U sj is the energy-saving heat transfer coefficient, A glass is the glass area, U glass is the heat transfer coefficient of the glass, A wall is the non-transparent wall area, U wall is the heat transfer coefficient of the non-transparent wall, A sum is the total area of the glass and the non-transparent wall;

[0017] The defect identification unit: compares the parameter values of the digital twin model with the design standards stored in the specification database unit in real time, and marks the fire passage region or the wall region of the digital twin model as a defect region when the fire passage width is less than the first threshold value or the energy-saving heat transfer coefficient is greater than the second threshold value;

[0018] The defect severity score S of the defect region is calculated:

[0019]

[0020] wherein, α and β are weight coefficients, α+β=1, W actual is the actual fire passage width, U actual is the actual energy-saving heat transfer coefficient;

[0021] When the defect severity score S is greater than the severity score threshold value S T , the design work is optimized.

[0022] Further, the dynamic optimization module generates an adjustment scheme by the following way:

[0023] The parameterized design template library is called to match the adjustment strategy corresponding to the defect type, including:

[0024] When the fire passage width is less than the first threshold, generate the following solution:

[0025]

[0026] Among them, W new is the width of the fire escape after the wall is moved, Δx is the distance the wall needs to be moved, N is the number of escape hatches to be added, and L path is the total length of the fire passage, N min is the minimum number of escape hatches;

[0027] When the energy-saving heat transfer coefficient is greater than the second threshold, a solution is generated:

[0028]

[0029] Genetic algorithm is used to iteratively generate parameter combinations that meet multiple constraints.

[0030] Furthermore, the specific steps of iteratively generating a parameter combination that satisfies multiple constraints using a genetic algorithm include:

[0031] Construct chromosomes containing fire escape and energy-saving heat transfer adjustment parameters;

[0032] Optimization objective function:

[0033]

[0034] Among them, maxF(K) is the objective function, ω1, ω2 and ω3 are weights, ω1+ω2+ω3=1, is the normalized correction cost, is the normalized environmental improvement value, Normalized user preference matching degree;

[0035] Iteratively perform selection-crossover-mutation operations until convergence, and output the Pareto optimal solution set;

[0036] The optimal solution set is the final optimized solution.

[0037] Furthermore, the specific steps of generating several parameter adjustment schemes for each defective area and calculating the correction cost ΔC and environmental improvement value ΔE of each scheme include:

[0038] The correction cost ΔC is calculated as follows:

[0039]

[0040] Among them, k i is the unit modified cost coefficient of the i-th type of solution, Δv i is the adjustment amount of the i-th type of solution, di is the construction environment complexity factor, C fixed is a fixed cost;

[0041] The environmental improvement value ΔE is calculated as follows:

[0042]

[0043] Among them, w k is the weight, e i The actual parameter value of the material used for the i-th type solution, y i Industry benchmark values ​​for materials used for Category I solutions.

[0044] Furthermore, the user preference matching degree P is obtained by collecting the user's historical operation data, obtaining the user's historical material selection frequency, the user's historical design style selection and the user's historical average acceptance cost increase, and obtaining the material similarity by weighted summation of the user's historical material selection frequency. The calculation formula is:

[0045]

[0046] Among them, Sim mater is the material similarity, f j Mat j The usage ratio in the current solution,||(Mat j ∈Φ) is a function, which indicates that the material is 1 if it is in the user's historical preference set Φ, otherwise it is 0, where Φ is the user's historical preference set, i.e., the set of materials that the user frequently uses;

[0047] Then, the user’s preferred style vector is obtained by selecting the design style from the user’s history, and the style similarity is calculated using the vector space cosine similarity. The calculation formula is:

[0048]

[0049] Among them, Sim style is the style similarity, V user is the user preference style vector, V sol is the style vector of the current scheme;

[0050] Then, the cost sensitivity is calculated based on the user's historical average acceptance cost increase. The formula is:

[0051]

[0052] Among them, Sim cost is the cost sensitivity, exp() is the natural exponential function, ΔC is the correction cost, μ c is the historical average acceptance cost increase of users, σ cAccepting standard deviation of fluctuations for user costs;

[0053] Finally, the user preference matching degree is calculated as follows:

[0054] P=α·Sim mater +β·Sim style +γ·Sim cost ;

[0055] Where P is the user preference matching degree, α, β and γ are weights, and α+β+γ=1.

[0056] Furthermore, the interactive display module includes:

[0057] Three-dimensional difference unit, using red-yellow-green scale to identify the areas with defect severity score S from high to low;

[0058] Scheme comparison unit, used to display the cost change rate before and after optimization in real time;

[0059] The voice interaction unit is used to respond to the optimization instruction and synchronously update the model, wherein the optimization instruction includes selection plan A, selection plan B, selection plan C and selection plan D.

[0060] A method for displaying environmental design works, comprising:

[0061] S1. Use a 3D laser scanner to scan the design work, obtain point cloud data, build a digital twin model based on the point cloud data, and extract spatial structure parameters and material property parameters;

[0062] S2. Detect the digital twin model, identify the design defect area, calculate the defect severity score S of the defect area, and set the defect severity score threshold S T , when the calculated defect severity score S is greater than the severity score threshold S T Dynamically repair the design works;

[0063] S3. Generate several parameter adjustment schemes for each defect area and calculate the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P of each scheme;

[0064] S4. Normalize the corrected cost ΔC, the environmental improvement value ΔE, and the user preference matching degree P to obtain a decision matrix, and synthesize the decision matrix to obtain the optimal solution;

[0065] S5. Synchronously display the original design, optimized solution, and key indicator comparison data in a side-by-side view, allowing users to select and apply the optimized solution in real time.

[0066] Furthermore, the optimization solution generation includes:

[0067] When the insufficient width of the fire access is detected, two adjustment schemes of the translation wall and the additional escape opening are generated;

[0068] When the substandard energy-saving heat transfer coefficient is detected, two adjustment schemes of replacing the glass type and reducing the glass area are generated.

[0069] Further, it further comprises:

[0070] Record the user-selected optimization scheme and manually modify the path;

[0071] Update the user preference model according to the recorded data to improve the accuracy of subsequent recommendations.

[0072] The technical scheme provided by the application has the following beneficial effects compared with the known prior art:

[0073] 1. The application generates a digital twin model through three-dimensional laser scanning, automatically detects key parameters such as the width of the fire access and the energy-saving heat transfer coefficient in combination with the specification database, and calculates the defect severity score to realize the precision of problem positioning and the priority sorting;

[0074] 2. A variety of adjustment schemes are generated for defects, such as translating the wall and replacing the glass type, and based on the genetic algorithm optimization objective function, the cost, environmental improvement value and user preference matching degree are comprehensively corrected, and the Pareto optimal solution set is output to ensure the balance of economic efficiency, environmental protection and personalized demand;

[0075] 3. The original design and the optimization scheme are compared through side-by-side view, supplemented by red-yellow-green color scale marking of defect severity, supporting real-time adjustment of the model through voice instructions, reducing the user operation threshold and improving the decision-making efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0076] In order to more clearly illustrate the technical schemes in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0077] Figure 1 The module schematic diagram of the application;

[0078] Figure 2 The flowchart of the application. DETAILED DESCRIPTION

[0079] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0080] The present invention will be further described below with reference to the embodiments.

[0081] Example 1: Reference Figure 1 , an environmental design work display system, comprising:

[0082] The model extraction module uses a 3D laser scanner to scan the design model, obtain point cloud data, and generate a digital twin model;

[0083] Intelligent detection module, used to detect digital twin models, identify design defect areas, calculate the defect severity score S of the defect area, and set the defect severity score threshold S T , when the calculated defect severity score S is greater than the severity score threshold S T Dynamically repair the design works;

[0084] The dynamic optimization module generates several parameter adjustment schemes for each defect area, calculates the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P of each scheme, and normalizes the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P to generate a decision matrix, including the correction cost score. Environmental improvement score User preference rating The optimal solution is obtained by integrating the decision matrix;

[0085] The interactive display module displays the original design, optimized solutions, and key indicator comparison data in a side-by-side view, allowing users to select and apply optimized solutions in real time.

[0086] In a specific embodiment, a 3D laser scanner is used to scan the lobby on the first floor of a commercial complex to obtain point cloud data including glass curtain walls, fire escapes, and decorative columns, generate a digital twin model, and extract parameters: the actual fire escape width W actual =1.2m, standard threshold W = 1.5m, glass area A glass =400m 2 , non-transparent wall area A wall =300m 2, the current glass heat transfer coefficient and wall heat transfer coefficient, and mark the fire escape (red) and glass curtain wall (yellow) areas to be optimized in the visualization model;

[0087] Furthermore, the intelligent detection module includes:

[0088] The standard database unit uses a sub-library architecture to store design standards. The design standards include a first threshold W and a second threshold U. The first threshold is the fire passage width threshold, and the second threshold is the energy-saving heat transfer coefficient threshold.

[0089] The fire escape width is obtained from the digital twin model data, and the energy-saving heat transfer coefficient is obtained using the following formula:

[0090]

[0091] Among them, U sj is the energy-saving heat transfer coefficient, A glass is the glass area, U glass is the heat transfer coefficient of glass, A wall is the area of ​​non-transparent wall, U wall is the heat transfer coefficient of the non-transparent wall, A sum is the total area of ​​glass and non-transparent walls;

[0092] Defect identification unit: This unit compares the parameter values ​​of the digital twin model with the design standards stored in the specification database unit in real time. When the fire passage width is less than a first threshold or the energy-saving heat transfer coefficient is greater than a second threshold, the fire passage area or wall area of ​​the digital twin model is marked as a defective area.

[0093] Calculate the defect severity score S of the defect area:

[0094]

[0095] Among them, α and β are weight coefficients, α+β=1, W actual is the actual width of the fire passage, U actual is the actual energy-saving heat transfer coefficient;

[0096] When the defect severity score S is greater than the severity score threshold S T When optimizing the design work.

[0097] In a specific embodiment, the calculated energy-saving heat transfer coefficient meets the threshold standard and is up to standard, and the fire passage width 1.2m<1.5m is marked as defective;

[0098] Calculate the defect severity score S, with a weight of α = 0.6. The fire protection weight is higher, β = 0.4, and the formula is:

[0099]

[0100] severity score threshold S T = 0.1, since S > S T , optimization is triggered, and the system prompts: the fire passage width is insufficient and needs to be optimized.

[0101] Further, the dynamic optimization module generates an adjustment scheme by the following ways:

[0102] Calling the parametric design template library, matching the adjustment strategy corresponding to the defect type, including:

[0103] When the fire passage width is less than the first threshold, the scheme is generated:

[0104]

[0105] Wherein, W new is the fire passage width after the wall translation, Δx is the distance the wall needs to be translated, N is the number of escape openings that need to be added, L path is the total length of the fire passage, N min is the minimum value of the number of escape openings;

[0106] When the energy-saving heat transfer coefficient is greater than the second threshold, the scheme is generated:

[0107]

[0108] The genetic algorithm is used to iteratively generate parameter combinations that meet multiple constraint conditions.

[0109] Further, the specific steps of using the genetic algorithm to iteratively generate parameter combinations that meet multiple constraint conditions include:

[0110] Constructing a chromosome containing the fire passage and energy-saving heat adjustment parameters;

[0111] Optimizing the objective function:

[0112]

[0113] Wherein, maxF(K) is the objective function, ω1, ω2 and ω3 are weights, ω1+ω2+ω3=1, is the normalized correction cost, is the normalized environmental improvement value, is the normalized user preference matching degree;

[0114] Iteratively performing selection, crossover and mutation operations until convergence, and outputting a Pareto optimal solution set;

[0115] The optimal solution set is the final optimized scheme.

[0116] In a specific embodiment, an adjustment plan is generated for the fire escape problem, including:

[0117] Solution A: Translation wall, Δx = 0.3m, W new =1.5m, modified cost ΔC = 8000 yuan, including construction complexity factor d i =1.2;

[0118] Plan B: Add an escape hatch. Correction cost ΔC = 5000 yuan;

[0119] Regarding the fire escape issue, although it meets the standards, the user requires improvement, so an adjustment plan is generated, including:

[0120] Plan C: Replace the glass with vacuum glass, ΔE=1.1, ΔC=20,000 yuan;

[0121] Plan D: Reduce the glass area by 10%, ΔE=0.5, ΔC=12,000 yuan.

[0122] Furthermore, the specific steps of generating several parameter adjustment schemes for each defect area and calculating the correction cost ΔC and environmental improvement value ΔE of each scheme include:

[0123] Correction cost ΔC, calculated as:

[0124]

[0125] Among them, k i is the unit modified cost coefficient of the i-th type of solution, Δv i is the adjustment amount of the i-th type of solution, d i is the construction environment complexity factor, C fixed is a fixed cost;

[0126] The environmental improvement value ΔE is calculated as follows:

[0127]

[0128] Among them, w k is the weight, e i The actual parameter value of the material used for the i-th type solution, y i Industry benchmark values ​​for materials used for Category I solutions.

[0129] Furthermore, the user preference matching degree P is obtained by collecting the user's historical operation data, obtaining the frequency of the user's historical material selection, the user's historical design style selection and the user's historical average acceptance cost increase, and then taking the weighted sum of the frequency of the user's historical material selection to obtain the material similarity. The calculation formula is:

[0130]

[0131] Among them, Sim mater is the material similarity, f j Mat j The usage ratio in the current solution,||(Mat j ∈Φ) is a function, which indicates that the material is 1 if it is in the user's historical preference set Φ, otherwise it is 0, where Φ is the user's historical preference set, i.e., the set of materials that the user frequently uses;

[0132] Then, the user’s preferred style vector is obtained by selecting the design style from the user’s history, and the style similarity is calculated using the vector space cosine similarity. The calculation formula is:

[0133]

[0134] Among them, Sim style is the style similarity, V user is the user preference style vector, V sol is the style vector of the current scheme;

[0135] Then, the cost sensitivity is calculated based on the user's historical average acceptance cost increase. The formula is:

[0136]

[0137] Among them, Sim cost is the cost sensitivity, exp() is the natural exponential function, ΔC is the correction cost, μ c is the historical average acceptance cost increase of users, σ c Accepting standard deviation of fluctuations for user costs;

[0138] Finally, the user preference matching degree is calculated as follows:

[0139] P=α·Sim mater +β·Sim style +γ·Sim cost ;

[0140] Where P is the user preference matching degree, α, β and γ are weights, and α+β+γ=1.

[0141] In a specific embodiment, multi-objective decision making is performed, user preference data is obtained, and the historical selection is “low cost first”. c =10%,σ c =2%, style preference is "modern simplicity", V user =[0.9, 0.1];

[0142] Calculate the matching degree of solution B+D:

[0143] Material similarity Sim mater = 0.7, the scheme uses 60% of the user's commonly used aluminum plate;

[0144] Style similarity Sim style = 0.95, the scheme vector V sol = [0.85, 0.15];

[0145] Cost sensitivity ΔC = 12000 yuan, total cost increase 17%;

[0146] User preference matching degree P = 0.5x0.7 + 0.3x0.95 + 0.2x0.67 = 0.784, the genetic algorithm outputs the optimal solution: scheme B+D, the comprehensive score F(K) = 0.82, the system displays the recommended scheme: "translation wall + reduce glass area", the total cost increases by 17000 yuan, the fire reaches the standard and the heat transfer coefficient decreases to 1.98 W / (m 2 ·K).

[0147] Further, the interactive display module comprises:

[0148] Three-dimensional difference unit, using red-yellow-green color scale to identify the area of defect severity score S from high to low;

[0149] Scheme comparison unit, for real-time display of cost change rate before and after optimization;

[0150] Voice interaction unit, for responding to optimization instructions and synchronously updating the model, the optimization instructions including selecting scheme A, selecting scheme B, selecting scheme C and selecting scheme D.

[0151] In one specific embodiment, the interactive display module comprises:

[0152] Three-dimensional comparison: original model, fire passage marked red (defect), glass curtain wall marked yellow (suggested optimization); optimized model, fire passage widened to 1.5m (green), glass area reduction area highlighted;

[0153] Data panel: real-time display of cost change, +17000 yuan (+14%); environmental improvement value ΔE = 0.8;

[0154] Voice interaction: user instruction, "view scheme A+C", the system switches to display and update the cost, +28000 yuan; final instruction, "apply scheme B+D", the system saves the selection and updates the user preference library.

[0155] Embodiment two: reference Figure 2 A method for displaying environmental design works, comprising:

[0156] S1. Use a 3D laser scanner to scan the design work, obtain point cloud data, build a digital twin model based on the point cloud data, and extract spatial structure parameters and material property parameters;

[0157] S2. Detect the digital twin model, identify the design defect area, calculate the defect severity score S of the defect area, and set the defect severity score threshold S T , when the calculated defect severity score S is greater than the severity score threshold S T Dynamically repair the design works;

[0158] S3. Generate several parameter adjustment schemes for each defect area and calculate the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P of each scheme;

[0159] S4. Normalize the corrected cost ΔC, the environmental improvement value ΔE, and the user preference matching degree P to obtain a decision matrix, and synthesize the decision matrix to obtain the optimal solution;

[0160] S5. Synchronously display the original design, optimized solution, and key indicator comparison data in a side-by-side view, allowing users to select and apply the optimized solution in real time.

[0161] Furthermore, the optimization solution generation includes:

[0162] When it is detected that the fire passage is not wide enough, two adjustment plans are generated: moving the wall horizontally or adding an escape hatch;

[0163] When it is detected that the energy-saving heat transfer coefficient does not meet the standard, two adjustment plans are generated: changing the glass type and reducing the glass area.

[0164] Furthermore, it also includes:

[0165] Record the optimization plan and manual modification path selected by the user;

[0166] Update the user preference model based on recorded data to improve the accuracy of subsequent recommendations.

[0167] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An environmental design work display system, characterized in that: include: The model extraction module uses a 3D laser scanner to scan the design model, obtain point cloud data, and generate a digital twin model; Intelligent detection module, used to detect digital twin models, identify design defect areas, calculate the defect severity score S of the defect area, and set the defect severity score threshold S T , when the calculated defect severity score S is greater than the severity score threshold S T Dynamically repair the design works; The dynamic optimization module generates several parameter adjustment schemes for each defect area, calculates the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P of each scheme, and normalizes the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P to generate a decision matrix, including the correction cost score. Environmental improvement score User preference rating The optimal solution is obtained by integrating the decision matrix; The interactive display module displays the original design, optimized solutions, and key indicator comparison data in a side-by-side view, allowing users to select and apply optimized solutions in real time.

2. The environmental design work display system according to claim 1, characterized in that: The intelligent detection module includes: A standard database unit adopts a sub-library architecture to store design standards, wherein the design standards include a first threshold value W and a second threshold value U, wherein the first threshold value is a fire passage width threshold value, and the second threshold value is an energy-saving heat transfer coefficient threshold value; The fire passage width is obtained from the digital twin model data, and the energy-saving heat transfer coefficient is obtained by the following formula: Among them, U sj is the energy-saving heat transfer coefficient, A glass is the glass area, U glass is the heat transfer coefficient of glass, A wall is the area of ​​non-transparent wall, U wall is the heat transfer coefficient of the non-transparent wall, A sum is the total area of ​​glass and non-transparent walls; Defect identification unit: This unit compares the parameter values ​​of the digital twin model with the design standards stored in the specification database unit in real time. When the fire passage width is less than a first threshold or the energy-saving heat transfer coefficient is greater than a second threshold, the fire passage area or wall area of ​​the digital twin model is marked as a defective area. Calculate the defect severity score S of the defect area: Among them, α and β are weight coefficients, α+β=1, W actual is the actual width of the fire passage, U actual is the actual energy-saving heat transfer coefficient; When the defect severity score S is greater than the severity score threshold S T When optimizing the design work.

3. The environmental design work display system according to claim 1, characterized in that: The dynamic optimization module generates an adjustment plan in the following way: Call the parametric design template library to match the adjustment strategy corresponding to the defect type, including: When the fire passage width is less than the first threshold, generate the following solution: Among them, W new is the width of the fire escape after the wall is moved, Δx is the distance the wall needs to be moved, N is the number of escape hatches to be added, and L path is the total length of the fire passage, N min is the minimum number of escape hatches; When the energy-saving heat transfer coefficient is greater than the second threshold, a solution is generated: Genetic algorithm is used to iteratively generate parameter combinations that meet multiple constraints.

4. The environmental design work display system according to claim 3, characterized in that: The specific steps of iteratively generating parameter combinations that meet multiple constraints using a genetic algorithm include: Construct chromosomes containing fire escape and energy-saving heat transfer adjustment parameters; Optimization objective function: Among them, maxF(K) is the objective function, ω1, ω2 and ω3 are weights, ω1+ω2+ω3=1, is the normalized correction cost, is the normalized environmental improvement value, Normalized user preference matching degree; Iteratively perform selection-crossover-mutation operations until convergence, and output the Pareto optimal solution set; The optimal solution set is the final optimized solution.

5. The environmental design work display system according to claim 1, characterized in that: The specific steps of generating several parameter adjustment schemes for each defect area and calculating the correction cost ΔC and environmental improvement value ΔE of each scheme include: The correction cost ΔC is calculated as follows: Among them, k i is the unit modified cost coefficient of the i-th type of solution, Δv i is the adjustment amount of the i-th type of solution, d i is the construction environment complexity factor, C fixed is a fixed cost; The environmental improvement value ΔE is calculated as follows: Among them, w k is the weight, e i The actual parameter value of the material used for the i-th type solution, y i Industry benchmark values ​​for materials used for Category I solutions.

6. The environmental design work display system according to claim 1, characterized in that: The user preference matching degree P is obtained by collecting the user's historical operation data, obtaining the user's historical material selection frequency, the user's historical design style selection and the user's historical average acceptance cost increase, and then taking the weighted sum of the user's historical material selection frequency to obtain the material similarity. The calculation formula is: Among them, Sim mater is the material similarity, f j Material Mat j The usage ratio in the current solution,||(Mat j ∈Φ) is a function, which indicates that the material is 1 if it is in the user's historical preference set Φ, otherwise it is 0, where Φ is the user's historical preference set, i.e., the set of materials that the user frequently uses; Then, the user’s preferred style vector is obtained by selecting the design style from the user’s history, and the style similarity is calculated using the vector space cosine similarity. The calculation formula is: Among them, Sim style is the style similarity, V user is the user preference style vector, V sol is the style vector of the current scheme; Then, the cost sensitivity is calculated based on the user's historical average acceptance cost increase. The formula is: Among them, Sim cost is the cost sensitivity, exp() is the natural exponential function, ΔC is the correction cost, μ c is the historical average acceptance cost increase of users, σ c Accepting standard deviation of fluctuations for user costs; Finally, the user preference matching degree is calculated as follows: P=α·Yes mater +β·Yes style +γ·Yes cost ; Where P is the user preference matching degree, α, β and γ are weights, and α+β+γ=1.

7. The environmental design work display system according to claim 1, characterized in that: The interactive display module includes: Three-dimensional difference unit, using red-yellow-green scale to identify the areas with defect severity score S from high to low; Scheme comparison unit, used to display the cost change rate before and after optimization in real time; The voice interaction unit is used to respond to the optimization instruction and synchronously update the model, wherein the optimization instruction includes selection plan A, selection plan B, selection plan C and selection plan D.

8. A method for displaying environmental design works, characterized in that: include: S1. Use a 3D laser scanner to scan the design work, obtain point cloud data, build a digital twin model based on the point cloud data, and extract spatial structure parameters and material property parameters; S2. Detect the digital twin model, identify the design defect area, calculate the defect severity score S of the defect area, and set the defect severity score threshold S T , when the calculated defect severity score S is greater than the severity score threshold S T Dynamically repair the design works; S3. Generate several parameter adjustment schemes for each defect area and calculate the correction cost ΔC, environmental improvement value ΔE and user preference matching degree P of each scheme; S4. Normalize the corrected cost ΔC, the environmental improvement value ΔE, and the user preference matching degree P to obtain a decision matrix, and synthesize the decision matrix to obtain the optimal solution; S5. Synchronously display the original design, optimized solution, and key indicator comparison data in a side-by-side view, allowing users to select and apply the optimized solution in real time.

9. The method according to claim 7, characterized in that The optimization solution generation includes: When it is detected that the fire passage is not wide enough, two adjustment plans are generated: moving the wall horizontally or adding an escape hatch; When it is detected that the energy-saving heat transfer coefficient does not meet the standard, two adjustment plans are generated: changing the glass type and reducing the glass area.

10. The method according to claim 7, characterized in that Also includes: Record the optimization plan and manual modification path selected by the user; Update the user preference model based on recorded data to improve the accuracy of subsequent recommendations.

Images