CN116541942A

CN116541942A - Judgment method for building design optimization scheme

Info

Publication number: CN116541942A
Application number: CN202310821885.0A
Authority: CN
Inventors: 王淑芬; 于涛; 任佑彬; 李胜军; 任凤彦
Original assignee: Hebei Shiyuan Engineering Construction Consulting Co ltd
Current assignee: Hebei Shiyuan Engineering Construction Consulting Co ltd
Priority date: 2023-07-06
Filing date: 2023-07-06
Publication date: 2023-08-04
Anticipated expiration: 2043-07-06
Also published as: CN116541942B

Abstract

The invention relates to the technical field of building design data processing, in particular to a judging method for a building design optimization scheme. The method comprises the following steps: building design data are obtained, first evaluation standard data are generated according to the building design data, and first evaluation standard data are generated; building a model according to the building design data to build a building design model; performing first evaluation processing on the building design model by using first evaluation standard data to obtain first evaluation data, and performing evaluation processing on the building design model by using preset second evaluation standard data to obtain second evaluation data; and acquiring historical building design evaluation data, performing deep evaluation on the first evaluation data and the second evaluation data by utilizing the historical building design evaluation data, judging the generation of the improvement opinion, and acquiring building design optimization scheme judgment data. The invention provides better decision support and effect by providing accurate building design evaluation and optimization scheme judgment.

Description

Judgment method for building design optimization scheme

Technical Field

The invention relates to the technical field of building design data processing, in particular to a judging method for a building design optimization scheme.

Background

The method or process for judging the architectural design optimization scheme refers to a method or process for determining the advantages, the disadvantages, the feasibility and the improvement potential of the architectural design scheme through evaluation, analysis and comparison. It aims to help design teams, decision makers or stakeholders make informed decisions, select the best architectural design solution or optimize existing solutions. Information technology and computer science methods are utilized to support the evaluation, analysis, and decision making process of architectural designs. By digitizing, integrating and visualizing the architectural design data and related information, the informatization can provide more efficient, accurate and comprehensive architectural design optimization scheme decisions. Existing judgment methods for architectural design optimization schemes may only be applicable to specific types of architecture or specific design problems, and cannot be adapted to architectural designs of different types and complexities, which limits the broad applicability and applicability of the methods.

Disclosure of Invention

The invention provides a judging method for a building design optimization scheme to solve at least one technical problem.

The application provides a judging method for a building design optimization scheme, which comprises the following steps:

Step S1: building design data are obtained, and first evaluation standard data are generated according to the building design data, so that first evaluation standard data are generated;

step S2: building a model according to the building design data, thereby building a building design model;

step S3: performing first evaluation processing on the building design model by using first evaluation standard data so as to obtain first evaluation data, and performing evaluation processing on the building design model by using preset second evaluation standard data so as to obtain second evaluation data;

step S4: and acquiring historical building design evaluation data, performing deep evaluation on the first evaluation data and the second evaluation data by utilizing the historical building design evaluation data, and judging the generation of the improvement opinion, thereby acquiring building design optimization scheme judgment data.

The invention provides comprehensive building design evaluation, and through the steps S1 and S2, the method acquires building design data and builds a building design model, so that the building design scheme can be comprehensively evaluated. By comprehensively considering a plurality of evaluation data and model analysis, a more accurate and comprehensive evaluation result can be obtained. The first evaluation data generation and processing in steps S1 and S3 enables the rapid generation of evaluation data of a building design. This helps to quickly understand the merits of the design and provides basis for subsequent evaluation and decision making. And carrying out depth evaluation by combining the historical data, and carrying out depth evaluation on the first evaluation data and the second evaluation data by utilizing the historical building design evaluation data through step S4. This method of combining historical data can provide deeper analysis and evaluation, discover potential problems in the design, and generate improvement ideas to optimize the architectural design. Providing decision support, the building design optimization judgment data generated in the step S4 can provide important information about the building design for a design team, a decision maker or a stakeholder. The information can be used for guiding a decision making process, optimizing a design scheme, improving the quality and efficiency of the design, is high in universality and can adapt to building designs with different types and complexity.

Preferably, step S1 is specifically:

step S11: acquiring building design data;

step S12: building space distribution feature extraction and building appearance design feature extraction are carried out according to the building design data, so that the building space distribution feature data and the building appearance design feature data are obtained;

step S13: building use prediction is carried out according to the building space distribution characteristic data and the building appearance design characteristic data, so that building use prediction data are obtained;

step S14: and generating evaluation standard data according to the building use estimated data, so as to generate first evaluation standard data.

According to the invention, the building design data and the feature extraction are automatically acquired, so that the manual operation and the time consumption can be reduced, and the efficiency of the design flow is improved. Comprehensive evaluation: through the extraction of the spatial distribution characteristics of the building and the extraction of the design characteristics of the appearance of the building, various aspects of the design of the building, including spatial layout and design of the appearance, are comprehensively considered. And comprehensively evaluating the advantages and disadvantages of the design scheme. Building use prediction is carried out through building space distribution characteristic data and building appearance design characteristic data. This can help the designer predict and locate the use of the building at the beginning of the design to better meet the user's needs. And generating evaluation data, namely generating first evaluation standard data based on the building use estimated data. These evaluation data may include indicators of building performance, feasibility, and economy for evaluating feasibility and merits of the design. Providing decision support, by obtaining first assessment data, and performing depth assessment in combination with historical architectural design assessment data, improvement ideas and suggestions can be generated. This may provide more information and support for design decisions, helping designers optimize solutions and make informed decisions.

Preferably, the building design data is one or two of planar building design data and three-dimensional building design data, the building space distribution feature data is one or two of planar building space distribution feature data and three-dimensional building space distribution feature data, the building appearance design feature data is one or two of planar building appearance design feature data and three-dimensional building appearance design feature data, and the step S12 specifically comprises:

when the building design data is determined to be planar building design data, performing planar building space distribution feature extraction on the building design data to obtain planar building space distribution feature data, and performing planar building appearance design feature extraction on the building design data to obtain planar building appearance design feature data;

when the building design data is determined to be three-dimensional building design data, three-dimensional building space distribution feature extraction is performed on the building design data, so that three-dimensional building space distribution feature data are obtained, and three-dimensional building appearance design feature extraction is performed on the building design data, so that three-dimensional building appearance design feature data are obtained.

According to different types of building design data, the method respectively extracts the spatial distribution characteristic data of the planar building, the spatial distribution characteristic data of the three-dimensional building and the appearance design characteristic data of the planar building. Thus, key characteristic data of the building design can be obtained from different angles, and the analysis and evaluation dimensions are enriched. By acquiring the spatial distribution characteristic data of the planar building and the spatial distribution characteristic data of the three-dimensional building, the spatial layout characteristics in the building design can be comprehensively analyzed. Meanwhile, by acquiring the design characteristic data of the planar building appearance, the aesthetic property and design characteristic of the building appearance can be comprehensively considered. This comprehensive analysis helps to fully evaluate the merits of the architectural design. According to the type of the building design data, the method can adapt to the planar building design and the three-dimensional building design. This allows a wide range of applicability of the method, which can be applied to different types and forms of architectural designs. By extracting specific building space distribution characteristic data and appearance design characteristic data, the accuracy and precision of design analysis can be improved. The designer can more accurately understand and evaluate the characteristics and advantages of the design scheme, so that more targeted optimization and improvement can be performed. By acquiring building space distribution feature data and design feature data, a designer may make more informed decision-making based on these data. The feasibility and the adaptability of the design scheme are improved, and the blindness and the trial-and-error cost in the design are reduced.

Preferably, step S13 is specifically:

step S131: performing building purpose classification extraction according to the building design data, thereby obtaining building purpose classification data, wherein the building purpose classification data comprises residential building purpose classification data, commercial building purpose classification data, office building purpose classification data and educational building purpose classification data;

step S132: building use feature extraction is carried out according to the building space distribution feature data and the building appearance design feature data, so that building use feature data is obtained;

step S133: performing building purpose influence weight adjustment on the building purpose characteristic data by utilizing the building purpose classification data so as to obtain weighted building purpose characteristic data;

step S134: and carrying out weight calculation and building use prediction according to the weighted building use characteristic data, thereby obtaining building use prediction data.

According to the invention, building design data is used for classifying and extracting building uses, and the buildings are classified according to different uses such as residence, business, office, education and the like. This facilitates the differentiation and analysis of different types of buildings, providing accurate classification data for subsequent architectural use predictions. And extracting the characteristic information of the building application through the building space distribution characteristic data and the building appearance design characteristic data. Thus, the characteristics of the layout, space distribution, appearance design and the like of the building can be comprehensively considered, and more comprehensive data support is provided for building use prediction. And (3) weight adjustment is carried out on the building purpose characteristic data by utilizing the building purpose classification data, and the importance degree of different building purposes on the characteristics is considered. By adjusting the weight, the influence of different building uses on the characteristics can be reflected more accurately, and the accuracy of building use estimation is improved. And (5) carrying out weight calculation based on the weighted building use characteristic data, and carrying out building use estimation. Therefore, the application of the building can be judged more accurately, and accurate suggestions are provided for the optimization and decision-making of the design scheme. Potential problems can be found in advance and corresponding adjustment can be carried out through estimating the building purpose, and the quality and adaptability of the building design are improved.

Preferably, step S14 is specifically:

performing evaluation standard determination according to the building design data and a pre-stored local building use evaluation index data set to generate building use evaluation index data;

and adjusting the evaluation index weight according to the estimated building use data and the evaluation index data of the building use, thereby obtaining first evaluation standard data.

In the invention, the evaluation standard is determined according to the building design data and a pre-stored building use evaluation index data set. In this way, evaluation criteria can be established based on actual data and knowledge of previous building use evaluations, thereby improving the accuracy and reliability of the evaluation. And adjusting the weight of the evaluation index according to the estimated data of the building use and the evaluation index data of the building use. By adjusting the weight, the importance degree of different evaluation indexes can be reflected more accurately, the influence of a plurality of indexes on the building application is comprehensively considered, and the comprehensiveness and reliability of the evaluation result are improved. And obtaining first evaluation standard data through adjustment of the evaluation index weight. These data can be used to determine the merits of the architectural design and provide a reference for the selection and decision making of the optimization scheme. The first evaluation criterion data may reflect the behavior of the architectural design under different evaluation indicators, helping to find potential problems and room for improvement.

Preferably, the building purpose influence weight adjustment in step 133 is calculated by a building purpose influence weight calculation formula, wherein the building purpose influence weight calculation formula is specifically: classification for building purposes>Features for building purposes>Degree of influence of->Is a constant term->Design data feature item for architecture>The>Personal characteristic value->Design feature data for building>Personal characteristic value->Weight adjustment item for comprehensive characteristic data, +.>Average eigenvalues in the classification for a particular building use.

The invention constructs a building purpose influence weight calculation formula, which can quantify the influence degree of building purpose classification on building purpose characteristics by considering the characteristic items of building design data, the characteristic values of building space distribution characteristic data and building appearance design characteristic data and the comprehensive characteristic data weight adjustment items. The method is beneficial to evaluating and adjusting the building application, thereby providing beneficial information and guidance for judging and deciding the building design optimization scheme. The formula calculates the influence degree of building purpose classification on building purpose characteristics by calculating the function derivative of the building design data characteristic items, combining the characteristic values of the building space distribution characteristic data and the building appearance design characteristic data and integrating the characteristic data weight adjustment items. This may help to quantify The degree of influence of different building use classifications on specific features is evaluated and adjusted for building use. Average eigenvalue in the formulaAnd the>Personal characteristic value->Building design feature data +.>Personal characteristic value->And the like, which is used for considering the importance of different characteristic values in the influence degree calculation. By averaging the eigenvalues and squaring the sum of the squares of the eigenvalues and the eigenvalues, the eigenvalues can be normalized and weighted to more fully account for the effects of each eigenvalue. The calculation formula fully considers the constant term +.>Building design data feature item->Building spatial distribution characteristic data +.>Personal characteristic value->Building design feature data +.>Personal characteristic value->Weight adjustment item of comprehensive characteristic data>Average eigenvalue in a specific building use class +.>And the interaction relationship with each other, building design data characteristic item +.>Representing a characteristic value or a characteristic vector of the architectural design data. By different features of the architectural design data, +.>The input of the function and thus the final calculation result is affected. Building spatial distribution characteristic data +.>Personal characteristic value->Representing a specific feature in the building spatial distribution feature data. Different- >The value is multiplied by other parameters during the calculation, thereby affecting the result. Building design feature data +.>Personal characteristic value->Representing a specific feature in the architectural design feature data. Different->The value is multiplied by other parameters during the calculation, thereby affecting the result. Weight adjustment item of comprehensive characteristic data>For adjusting the relative importance of the individual characteristic values in the building use characteristic data. />The value of (2) is multiplied by other parameters and plays a regulating role in the calculation formula.

Preferably, step S2 is specifically:

step S21: cleaning the building design data to obtain building design cleaning data;

step S22: extracting relevant characteristics of the evaluation data of the building design data, thereby obtaining relevant characteristic data of the building design evaluation;

step S23: performing feature data preprocessing on the building design evaluation related feature data so as to obtain building design evaluation related feature preprocessing data;

step S24: and constructing a secondary building index model according to the building design evaluation related characteristic preprocessing data, so as to construct a building design model, wherein the secondary building index model comprises a comfort building index model, a practical building index model and an ornamental building index model.

According to the invention, through cleaning the building design data, noise, abnormal values and incomplete data can be removed, and the accuracy and reliability of the data are improved. This helps ensure the credibility of the building design model establishment and evaluation. By extracting the relevant features of the evaluation data in the architectural design data, key architectural design indicators and performance parameters can be captured. The extraction of these features can help identify and quantify key factors of the architectural design, providing a basis for the construction of architectural design models. Preprocessing the building design evaluation related feature data helps to optimize the representation and processing of the data. The preprocessing comprises normalization, standardization and missing value processing of data, so that the scale difference among different features can be eliminated, and the stability and the interpretability of the building design model are improved. By constructing a two-level building index model according to the building design evaluation related characteristic preprocessing data, a special model can be established for different evaluation indexes (such as comfort, practicability, ornamental value and the like). Such a model allows for finer assessment of building design and provides targeted optimization suggestions.

Preferably, step S3 is specifically:

Step S31: extracting first evaluation related data from the building design model according to the first evaluation standard data, thereby obtaining first evaluation related data;

step S32: performing first evaluation processing on the first evaluation related data by using the first evaluation standard data so as to acquire first evaluation data;

step S33: extracting second evaluation related data from the building design model according to preset second evaluation standard data, so as to obtain second evaluation related data;

step S34: and performing second evaluation processing on the second evaluation related data by using the second evaluation criterion data, thereby obtaining second evaluation data.

According to the first evaluation standard data, evaluation data related to a building design model are extracted. These data contain key indicators and performance parameters in the first evaluation result for further analysis and processing. And performing first evaluation standard processing, namely calculating, analyzing or converting the data to obtain a more specific evaluation result by using the first evaluation data. This helps to understand the performance and characteristics of the architectural design model in depth, providing the basis for subsequent optimization. And extracting evaluation data related to the building design model according to preset second evaluation standard data. The second evaluation criterion data may comprise different evaluation indicators or different evaluation methods for a more comprehensive evaluation of the architectural design. And processing the second evaluation related data by using the second evaluation standard data to obtain a second evaluation result. By integrating a plurality of evaluation indexes or evaluation methods, the advantages and disadvantages of the building design scheme can be evaluated more comprehensively, and a more comprehensive reference is provided for optimization.

Preferably, step S4 is specifically:

step S41: acquiring historical building design evaluation data, and performing data preprocessing on the historical building design evaluation data so as to acquire historical building design evaluation preprocessing data;

step S42: performing depth evaluation modeling according to the historical building design evaluation preprocessing data, so as to construct a depth building design evaluation model;

step S43: and carrying out depth evaluation on the first evaluation data and the second evaluation data by using a depth building design evaluation model and judging the generation of improvement opinion, thereby obtaining building design optimization scheme judgment data.

By utilizing a large amount of historical evaluation data, a model with deep learning capability can be established, and the quality and performance of a building design scheme can be predicted and evaluated more accurately. The depth evaluation model can provide a more comprehensive and objective evaluation result by considering more factors and complex correlations. The deep building design evaluation model may comprehensively evaluate the first evaluation data and the second evaluation data and generate a specific improvement opinion. This helps designers and decision makers to understand the merits and merits of architectural designs and provides specific directions and strategies for improvement to optimize the design. Based on the evaluation result and the improvement opinion of the depth evaluation model, scientific and objective decision support can be provided for designers, architects and decision makers. They can make informed decisions based on the evaluation results, optimize the architectural design, and improve the quality and effectiveness of the design.

Preferably, the depth evaluation modeling is performed by a depth building design evaluation calculation formula, wherein the depth building design evaluation calculation formula is specifically: evaluation result data for architectural design, < >>For evaluating the upper limit of the result data integration, +.>For evaluating the index quantity data, +.>Is->Weight term of the individual historical building design evaluation preprocessing data,/->As an exponential function +.>Is->Building space distribution characteristic data items corresponding to the individual historical building design evaluation preprocessing data are +.>Is->Building design feature data item corresponding to each historical building design evaluation preprocessing data, ++>For integrating self-variable terms +.>Parameter standard deviation term of preprocessing data for historical building design evaluation, +.>For function quantity data ++>For the initial item->Is->And (3) evaluating the functions.

The invention constructs a depth building design evaluation calculation formula which can comprehensively consider the influence of a plurality of evaluation indexes and is expressed by the combination of weight items and functionsThe importance and the interrelationship of different indexes are achieved. The historical architectural design in the formula evaluates the preprocessing data and the standard deviation of the parameters, so that the model can be helped to consider the historical experience and the reliability of the evaluation data, and the accuracy and the reliability of the evaluation result are improved. By adjusting the weight items, the parameter standard deviation and the evaluation function, different evaluation indexes and factors can be flexibly weighted and adjusted according to specific conditions so as to adapt to different building design requirements. The calculation formula fully considers the upper integral limit of the evaluation result data Evaluation index quantity data->First->Weight term of individual historical building design evaluation pretreatment data +.>Exponential function->First->Building space distribution characteristic data item corresponding to each historical building design evaluation preprocessing data>First->Building design feature data item corresponding to each historical building design evaluation preprocessing data>Integral argument term->Parameter standard deviation term of historical building design evaluation preprocessing data +.>Function quantity data->Initial item->First->Individual evaluation function->And an interaction relationship with each other, wherein in the calculation formula, mathematical parameters interact through mathematical symbols. For example, weight item->Sum of parameters standard deviation->For adjusting the importance and reliability of the evaluation index, function +.>For weighting or adjusting the evaluation result. These parameters interact in the formula through mathematical operations of multiplication, exponential function, integration, thereby affecting the final evaluation result. The selection and adjustment of parameters can be optimized according to specific situations and actual demands so as to achieve better evaluation effect and generation of a building design optimization scheme.

The invention has the beneficial effects that: by acquiring the building design data, generating first evaluation data and performing evaluation processing on the building design model by using preset second evaluation data, comprehensive evaluation on the building design scheme is realized. Such comprehensive evaluation can consider factors of various aspects including architectural design features, spatial distribution, design of appearance, etc., thereby more accurately judging the merits of architectural design. The method utilizes historical building design evaluation data to carry out deep evaluation on the first evaluation data and the second evaluation data, and judges that the improvement opinion is generated. By introducing historical data, the method can provide evaluation results and optimization scheme judgment with more reference values by referring to past building design experience and knowledge. The process of depth assessment may include more complex mathematical models and algorithms that further improve the accuracy and reliability of the assessment, involving the construction of architectural design models and the generation of optimization scheme decision data. By constructing the architectural design model, architectural design data can be better understood and analyzed, thereby providing a basis for subsequent evaluation and judgment. The generation of the optimization scheme judgment data depends on the comprehensive analysis of the depth evaluation and the historical data. The method for combining model construction and judgment can realize comprehensive analysis and evaluation of the building design scheme. The evaluation and judgment process in the method is carried out according to the preset second evaluation data and the historical data, so that personalized adjustment can be carried out according to specific evaluation indexes and requirements. Therefore, customized optimization scheme judgment data can be generated according to different building projects and requirements, and a building design optimization scheme which is more fit with actual conditions is provided. The invention is used for guiding decision making process, optimizing design scheme, improving design quality and efficiency, and being high in universality and capable of adapting to building designs with different types and complexity.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting implementations made with reference to the following drawings in which:

FIG. 1 is a flow chart illustrating steps of a method for determining a building design optimization in accordance with one embodiment;

FIG. 2 shows a step flow diagram of step S1 of an embodiment;

FIG. 3 shows a step flow diagram of step S13 of an embodiment;

FIG. 4 shows a step flow diagram of step S2 of an embodiment;

FIG. 5 shows a step flow diagram of step S3 of an embodiment;

fig. 6 shows a step flow diagram of step S4 of an embodiment.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

Referring to fig. 1 to 6, the present application provides a method for determining an optimization scheme of a building design, including the following steps:

in particular, for example, assuming a building project, building design data for plan, elevation, material selection and functional requirements of the project are collected. From these data, it is possible to perform building design evaluation such as evaluating the rationality of the building design, the degree of optimization of the functional layout, and generate first evaluation criterion data such as a score or an evaluation index.

in particular, modeling may be performed using Computer Aided Design (CAD) software or Building Information Model (BIM) software, for example, using collected building design data. A complete building design model can be constructed by drawing a three-dimensional model of a building, constructing a spatial distribution relationship, defining appearance design features and the like.

specifically, for example, based on the first evaluation criterion data, an evaluation process may be performed on the architectural design model. For example, comfort, utility and ornamental aspects of the building are evaluated and corresponding first evaluation data are generated. Then, according to the preset second evaluation criterion data, further evaluation processing is performed on the building design model, for example, the aspects of energy efficiency, sustainability and safety are evaluated, and the second evaluation data is acquired.

Specifically, historical architectural design assessment data, including past project design and related assessment data, is collected, for example. Using these historical data, a depth assessment can be made and an improvement opinion generated. For example, by counting and analyzing the historical data, the successful cases and problem points of the past design scheme can be known, and the comparison and the comprehensive analysis are performed by combining the first evaluation data and the second evaluation data, so that the building design optimization scheme judgment data is generated.

The invention provides comprehensive building design evaluation, and through the steps S1 and S2, the method acquires building design data and builds a building design model, so that the building design scheme can be comprehensively evaluated. By comprehensively considering a plurality of evaluation data and model analysis, a more accurate and comprehensive evaluation result can be obtained. The first evaluation criterion data generation and processing in steps S1 and S3 can quickly generate evaluation data of a building design. This helps to quickly understand the merits of the design and provides basis for subsequent evaluation and decision making. And carrying out depth evaluation by combining the historical data, and carrying out depth evaluation on the first evaluation data and the second evaluation data by utilizing the historical building design evaluation data through step S4. This method of combining historical data can provide deeper analysis and evaluation, discover potential problems in the design, and generate improvement ideas to optimize the architectural design. Providing decision support, the building design optimization judgment data generated in the step S4 can provide important information about the building design for a design team, a decision maker or a stakeholder. The information can be used for guiding a decision making process, optimizing a design scheme, improving the quality and efficiency of the design, is high in universality and can adapt to building designs with different types and complexity.

Preferably, step S1 is specifically:

step S11: acquiring building design data;

specifically, for example, in a building project, data relating to the building design, such as plan view, elevation view, construction view, decorative material selection, functional requirements, are collected. And acquiring data through a data input interface or a database.

specifically, for example, using the collected architectural design data, the extraction of architectural spatial distribution features and architectural design features may be performed. For example, spatial distribution characteristics such as layout of a building, functional distribution of a room, etc. are extracted from a plan view, and design characteristics of a building such as materials for a facade, window forms, and architectural shapes are extracted from an elevation view.

specifically, for example, the extracted building space distribution feature data and building design feature data may be used to make a prediction of the building use. For example, the building is estimated to be suitable for different uses such as business offices, houses, hotels and the like according to the characteristics of the room function distribution, the house layout and the building appearance, and building use estimated data is generated.

Specifically, the generation of the evaluation criterion data may be performed, for example, based on the building use prediction data. According to the estimated results of different building uses, the building design can be evaluated, such as evaluating the applicability, feasibility and economical aspects of the building design, and corresponding first evaluation data, such as scores or evaluation indexes, are generated.

specifically, for example, for planar architectural design data: extracting spatial distribution characteristics of a planar building: information of the number, area, shape and position of rooms in the plan view can be extracted; and (3) extracting appearance design features of the planar building: the information of wall materials, colors, the number of windows and positions in the plan view can be extracted.

Specifically, for example, for three-dimensional architectural design data: extracting spatial distribution characteristics of a three-dimensional building: the information of the height, floor number, room number, area, shape and position of the building can be extracted through the three-dimensional model; extracting appearance design features of a three-dimensional building: the information of wall materials, colors, the number of windows and positions in the perspective view can be extracted. And extracting features of the building elevation image by using an image processing technology. Through computer vision and image processing technology, the features of the vertical face of the three-dimensional building, such as three-dimensional building color distribution, three-dimensional building texture features and three-dimensional building line shapes, such as main color extraction by clustering calculation, three-dimensional building shape feature extraction by color using distribution conditions, texture extraction by a filter and edge detection algorithm, can be automatically extracted.

Preferably, step S13 is specifically:

specifically, for example, residential building use classification data extraction: judging whether the building is suitable for living or not by analyzing the information of the number, the area, the functions and the like of rooms contained in a building plane or a three-dimensional model; commercial building use classification data extraction: judging whether the building is suitable for commercial use or not by analyzing spatial distribution characteristics and appearance design characteristics of shops, offices, exhibition halls and the like in the building design; extracting office building use classification data: judging whether the building is suitable for being used as an office place or not by analyzing the spatial distribution characteristics and the appearance design characteristics of offices, meeting rooms, reception rooms and the like in the building design; educational building use classification data extraction: by analyzing the spatial distribution characteristics and appearance design characteristics of classrooms, libraries and laboratories in the building design, whether the building is suitable for being used as an education place is judged.

specifically, for example, building use feature extraction: feature data related to the use of the building can be extracted by analyzing spatial distribution features and appearance design features in the building design, such as information of the number of rooms, areas, heights, door and window positions.

specifically, for example, the weighted building use feature data can be obtained by performing weighting processing on the building use feature data according to the building use classification data in a machine learning manner, such as a linear model, a decision tree model, a neural network model and an ensemble learning algorithm, so as to accurately reflect the importance of different building uses to the features.

Specifically, the estimated building use data is obtained by calculating weights from the weighted building use feature data, and performing the estimated building use in combination with the historical evaluation data and the analysis model, for example. Calculating weights from the weighted building usage feature data: and (3) inputting the weighted building use feature data into a building use weight calculation model, and calculating weights according to the importance of different features to obtain weights corresponding to different building uses. Building use estimation is carried out by combining historical evaluation data and an analysis model: combining the calculated weight with the historical evaluation data, and establishing a building purpose prediction model in a machine learning and statistical analysis mode. The model may use historical evaluation data to learn the relationship between building features and building uses and use the feature data of the current design to make predictions to derive the likelihood of different building uses. Obtaining estimated building use data: and according to the building purpose prediction model, inputting the characteristic data of the current design into the model for prediction, and obtaining the possibility of different building purposes. And generating building purpose prediction data comprising possible building purposes and probability values thereof according to the prediction result.

Preferably, step S14 is specifically:

specifically, for example, the evaluation criterion determines: determining an evaluation standard suitable for the building use according to the current building design data and a pre-stored local building use evaluation index data set, such as indexes of safety, sustainability, comfort and economy, and generating building use evaluation index data; and (5) adjusting the weight of the evaluation index: the evaluation indexes can be weighted according to the estimated data of the building use so as to reflect the importance of different building uses to different evaluation indexes, thereby obtaining first evaluation data.

Specifically, for example, evaluation criteria are determined: the safety evaluation standard can be determined according to the building design data, such as the information of a firewall, a fire-fighting channel and an evacuation route, and related standards (such as building design specifications, fire-fighting laws and the like) formulated for building types, such as whether the safety evaluation standard accords with corresponding safety regulations or not; generating evaluation index data: feature information related to safety, such as the number of fire extinguishers, the number of emergency exits, the position of refuge layers, etc., can be extracted from the architectural design data and converted into safety evaluation index data; and (5) adjusting the weight of the evaluation index: the first evaluation standard data can be obtained by carrying out weighting processing on different safety evaluation indexes according to the estimated data of the building use and combining experience of field experts and related standards so as to reflect importance of different building uses on different safety indexes.

Preferably, the building purpose influence weight adjustment in step 133 is calculated by a building purpose influence weight calculation formula, wherein the building purpose influence weight calculation formula is specifically: classification for building purposes>Features for building purposes >Degree of influence of->Is a constant term->Design data feature item for architecture>The>Personal characteristic value->Design feature data for building>Personal characteristic value->Weight adjustment item for comprehensive characteristic data, +.>Average eigenvalues in the classification for a particular building use.

The invention constructs a building purpose influence weight calculation formula, which can quantify the influence degree of building purpose classification on building purpose characteristics by considering the characteristic items of building design data, the characteristic values of building space distribution characteristic data and building appearance design characteristic data and the comprehensive characteristic data weight adjustment items. The method is beneficial to evaluating and adjusting the building application, thereby providing beneficial information and guidance for judging and deciding the building design optimization scheme. The formula calculates the classification of building use by calculating the function derivative of the feature item of the building design data, combining the feature values of the feature data of the building space distribution and the feature data of the building appearance design, and the weight adjustment item of the comprehensive feature dataFeatures for building purposes>Is a function of the degree of influence of (a). This can help quantify the degree of impact of different building use classifications on a particular feature, thereby evaluating and adjusting the building use. Average eigenvalue in formula +. >And the>Personal characteristic value->Building design feature data +.>Personal characteristic value->And the like, which is used for considering the importance of different characteristic values in the influence degree calculation. By averaging the eigenvalues and squaring the sum of the squares of the eigenvalues and the eigenvalues, the eigenvalues can be normalized and weighted to more fully account for the effects of each eigenvalue. The calculation formula fully considers the constant term +.>Building design data feature item->Building spatial distribution characteristic data +.>Personal characteristic value->Building design feature data +.>Personal characteristic value->Weight adjustment item of comprehensive characteristic data>Average eigenvalue in a specific building use class +.>And the interaction relationship with each other, building design data characteristic item +.>Special for representing building design dataA symptom value or a feature vector. By different features of the architectural design data, +.>The input of the function and thus the final calculation result is affected. Building spatial distribution characteristic data +.>Personal characteristic value->Representing a specific feature in the building spatial distribution feature data. Different->The value is multiplied by other parameters during the calculation, thereby affecting the result. Building design feature data +. >Personal characteristic value->Representing a specific feature in the architectural design feature data. Different->The value is multiplied by other parameters during the calculation, thereby affecting the result. Weight adjustment item of comprehensive characteristic data>For adjusting the relative importance of the individual characteristic values in the building use characteristic data. />The value of (2) is multiplied by other parameters and plays a regulating role in the calculation formula.

Preferably, step S2 is specifically:

specifically, for example, building data cleaning: the building design data can be cleaned in a mode of removing repeated data, missing values and abnormal values, so that the accuracy and the reliability of subsequent analysis are ensured; building design cleaning data acquisition: the building design data obtained after cleaning is the building design cleaning data.

specifically, for example, evaluation data-related feature extraction: characteristic data related to evaluation, such as luminosity, landscape quality, air quality and the like, can be extracted through information on spatial distribution, modeling form, material selection and equipment configuration in the building design data; building design evaluation related characteristic data acquisition: the feature data related to the evaluation extracted from the building design data is the feature data related to the building design evaluation.

specifically, for example, feature data preprocessing: the related characteristic data of the building design evaluation can be subjected to pretreatment modes such as data cleaning, normalization and standardization so as to facilitate the training and application of a subsequent model; and (3) preprocessing data acquisition of building design evaluation related characteristics: and the pretreated data of the relevant characteristics of the building design evaluation obtained after pretreatment is the output result of the third step.

Specifically, for example, a two-stage building index model is constructed: the comfort building index model, the practicability building index model and the ornamental building index model can be constructed based on the building design evaluation related characteristic preprocessing data in the modes of machine learning, statistical analysis and the like so as to reflect the performances and the quality of the building in different aspects; building a building design model: the three building index models are combined to form a complete building design model which can be used for comprehensively evaluating and optimizing the building design. For example, when evaluating an office building, a comfort building index model may be used to evaluate comfort in terms of lighting, temperature, noise, etc.; evaluating the practicality of the aspects of functionality and flexibility of the building index model by using the practicability building index model; and (5) evaluating the ornamental value in aspects of appearance design, landscape quality and the like by using an ornamental value building index model.

Preferably, step S3 is specifically:

specifically, for example, first evaluation-related data extraction: data related to the first assessment, such as parameters of area, height, material, may be extracted from the architectural design model according to different requirements of the first assessment; first evaluation related data acquisition: the data related to the first evaluation extracted from the architectural design model is the first evaluation related data.

specifically, for example, the first evaluation process: the first evaluation related data can be evaluated according to preset evaluation standards and weights, for example, for safety evaluation, the safety performance of fire prevention and the like of the building design model can be evaluated according to the corresponding standards and weights; first evaluation data acquisition: the first evaluation data obtained after the evaluation processing is the output result of the step.

Specifically, for example, the second evaluation-related data extraction: data related to the second evaluation, such as floor height, number of parking spaces, maintenance cost, can be extracted from the architectural design model according to a preset second evaluation data requirement; second evaluation related data acquisition: the data related to the second evaluation extracted from the architectural design model is the second evaluation related data.

Specifically, for example, the second evaluation process: the second evaluation related data may be evaluated according to a preset evaluation standard and weight, for example, for economic evaluation, the evaluation may be performed according to an index of maintenance cost and return on investment; second evaluation data acquisition: the second evaluation data obtained after the evaluation processing is the output result of the step.

Preferably, step S4 is specifically:

specifically, for example, historical architectural design evaluation data acquisition: relevant design evaluation data, such as safety, comfort, economy, etc., can be collected from historical building projects; data preprocessing: the collected historical building design evaluation data can be subjected to a cleaning, normalization and standardization pretreatment mode so as to facilitate the training and application of a subsequent model; historical architectural design evaluation preprocessing data acquisition: the history building design evaluation preprocessing data obtained after preprocessing is the output result of the step.

specifically, for example, depth estimation modeling: the deep learning technology and other technologies can be used, the preprocessing data are evaluated based on the historical building design, and a deep building design evaluation model is constructed, and the model can better predict the performances and the quality of the building design in different aspects through learning the rules and the relations in the historical data; building a building design evaluation model: after training, the obtained depth building design evaluation model is the output result of the step, and the model can be used for evaluating and optimizing new building designs.

Specifically, for example, depth estimation: the first evaluation data and the second evaluation data can be subjected to depth evaluation by utilizing the constructed depth building design evaluation model so as to reflect the performance and quality of the first evaluation data and the second evaluation data in practical application; and (3) generating improvement opinion: according to the depth evaluation result, building design optimization scheme judgment data can be generated, and specific improvement suggestions can be given, for example, when an office building is evaluated, if the depth evaluation finds that the lighting is insufficient, the improvement suggestions of adding windows and using bright colors can be given; and (3) acquiring building design optimization scheme judgment data: and obtaining building design optimization scheme judgment data after depth evaluation and improvement opinion generation, wherein the judgment data is the output result of the step.

Preferably, wherein the depth estimation modeling is modeled by a depth building design estimation calculation formula, wherein the depth building design estimation calculation formula hasThe body is as follows: evaluation result data for architectural design, < >>For evaluating the upper limit of the result data integration, +.>For evaluating the index quantity data, +.>Is->Weight term of the individual historical building design evaluation preprocessing data,/->As an exponential function +.>Is->Building space distribution characteristic data items corresponding to the individual historical building design evaluation preprocessing data are +.>Is->Building design feature data item corresponding to each historical building design evaluation preprocessing data, ++>For integrating self-variable terms +.>Parameter standard deviation term of preprocessing data for historical building design evaluation, +.>For function quantity data ++>For the initial item->Is->And (3) evaluating the functions.

The invention constructs a depth building design evaluation calculation formula which can comprehensively consider the influence of a plurality of evaluation indexes and express the importance and the interrelationship of different indexes through the combination of weight items and functions. The historical architectural design in the formula evaluates the preprocessing data and the standard deviation of the parameters, so that the model can be helped to consider the historical experience and the reliability of the evaluation data, and the accuracy and the reliability of the evaluation result are improved. By adjusting the weight items, the parameter standard deviation and the evaluation function, different evaluation indexes and factors can be flexibly weighted and adjusted according to specific conditions so as to adapt to different building design requirements. The calculation formula fully considers the upper integral limit of the evaluation result data Evaluation index quantity data->First->Weight term of individual historical building design evaluation pretreatment data +.>Exponential function->First->History of individualsBuilding design evaluation preprocessing data corresponding building space distribution characteristic data item>First->Building design feature data item corresponding to each historical building design evaluation preprocessing data>Integral argument term->Parameter standard deviation term of historical building design evaluation preprocessing data +.>Function quantity data->Initial item->First->Individual evaluation function->And an interaction relationship with each other, wherein in the calculation formula, mathematical parameters interact through mathematical symbols. For example, weight item->Sum of parameters standard deviation->For adjusting the importance and reliability of the evaluation index, function +.>For weighting or adjusting the evaluation result. These parameters are calculated in the formula by multiplication,Mathematical operations of the exponential function, the integral interact, thereby affecting the final evaluation result. The selection and adjustment of parameters can be optimized according to specific situations and actual demands so as to achieve better evaluation effect and generation of a building design optimization scheme.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The judging method for the building design optimization scheme is characterized by comprising the following steps of:

2. The method according to claim 1, wherein step S1 is specifically:

step S11: acquiring building design data;

3. The method according to claim 2, wherein the architectural design data is one or both of planar architectural design data and stereoscopic architectural design data, the architectural spatial distribution feature data is one or both of planar architectural spatial distribution feature data and stereoscopic architectural spatial distribution feature data, and the architectural appearance design feature data is one or both of planar architectural appearance design feature data and stereoscopic architectural appearance design feature data, and step S12 is specifically:

4. The method according to claim 2, wherein step S13 is specifically:

5. The method according to claim 2, wherein step S14 is specifically:

6. The method of claim 4, wherein the building purpose impact weight adjustment in step 133 is calculated by a building purpose impact weight calculation formula, wherein the building purpose impact weight calculation formula is specifically: classification for building purposes>Features for building purposes>Degree of influence of->Is a constant term->Design data feature item for architecture>The>Personal characteristic value->Design feature data for building>Personal characteristic value->Weight adjustment item for comprehensive characteristic data, +.>Average eigenvalues in the classification for a particular building use.

7. The method according to claim 1, wherein step S2 is specifically:

cleaning the building design data to obtain building design cleaning data;

extracting relevant characteristics of the evaluation data of the building design data, thereby obtaining relevant characteristic data of the building design evaluation;

performing feature data preprocessing on the building design evaluation related feature data so as to obtain building design evaluation related feature preprocessing data;

And constructing a secondary building index model according to the building design evaluation related characteristic preprocessing data, so as to construct a building design model, wherein the secondary building index model comprises a comfort building index model, a practical building index model and an ornamental building index model.

8. The method according to claim 1, wherein step S3 is specifically:

extracting first evaluation related data from the building design model according to the first evaluation standard data, thereby obtaining first evaluation related data;

performing first evaluation processing on the first evaluation related data by using the first evaluation standard data so as to acquire first evaluation data;

extracting second evaluation related data from the building design model according to preset second evaluation standard data, so as to obtain second evaluation related data;

and performing second evaluation processing on the second evaluation related data by using the second evaluation criterion data, thereby obtaining second evaluation data.

9. The method according to claim 1, wherein step S4 is specifically:

acquiring historical building design evaluation data, and performing data preprocessing on the historical building design evaluation data so as to acquire historical building design evaluation preprocessing data;

Performing depth evaluation modeling according to the historical building design evaluation preprocessing data, so as to construct a depth building design evaluation model;

and carrying out depth evaluation on the first evaluation data and the second evaluation data by using a depth building design evaluation model and judging the generation of improvement opinion, thereby obtaining building design optimization scheme judgment data.

10. The method of claim 9, wherein the depth estimation modeling is modeled by a depth building design estimation calculation formula, wherein the depth building design estimation calculation formula is specifically: evaluation result data for architectural design, < >>For evaluating the upper limit of the result data integration, +.>For evaluating the index quantity data, +.>Is->Weight term of the individual historical building design evaluation preprocessing data,/->As an exponential function +.>Is->Building space distribution characteristic data items corresponding to the individual historical building design evaluation preprocessing data are +.>Is->Building design feature data item corresponding to each historical building design evaluation preprocessing data, ++>For integrating self-variable terms +.>Parameter standard deviation term of preprocessing data for historical building design evaluation, +.>For function quantity data ++>For the initial item->Is- >And (3) evaluating the functions.