Cost prediction methods, devices, equipment, media and products for energy-saving and carbon-reducing buildings

Abstract

The present application discloses a method, device, equipment, medium and product for predicting the construction cost of energy-saving and carbon-reducing buildings, which relates to the field of artificial intelligence technology. The method comprises: obtaining a first characteristic indicator and a first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator comprises: a conventional characteristic indicator of a construction project, the first characteristic data comprises: a conventional characteristic data of a construction project, the second characteristic indicator comprises: an incremental cost characteristic indicator of an energy-saving and carbon-reducing building, and the second characteristic data comprises: an incremental cost characteristic data of an energy-saving and carbon-reducing building; inputting the first characteristic data and the second characteristic data into an incremental cost prediction model for an energy-saving and carbon-reducing building to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building; inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for an energy-saving and carbon-reducing building to obtain the total cost information of the energy-saving and carbon-reducing building; wherein the incremental cost prediction model for an energy-saving and carbon-reducing building and the total cost prediction model for an energy-saving and carbon-reducing building are machine learning models constructed based on an SVR algorithm.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, medium and product for predicting the cost of energy-saving and carbon-reducing buildings. Background Art

[0002] According to a report by the United Nations Environment Programme, carbon emissions from buildings account for about 37% of the world's total carbon emissions. In my country, carbon emissions from buildings account for 50.9% of the country's total carbon emissions. It can be seen that the construction industry has become one of the largest carbon emission industries.

[0003] In the construction industry, the cost of construction projects has always been the top priority for all project participants to pay attention to and manage. For traditional non-energy-saving and carbon-reducing buildings, my country has a large number of completed cases that can be used as a reference and forecast for the construction cost of new projects. Different from the cost formula of traditional buildings, energy-saving and carbon-reducing buildings have become an emerging architectural concept in recent years. Energy-saving and carbon-reducing technologies run through the entire life cycle of building construction. The use of green building materials, energy-saving equipment, environmentally friendly construction technology and other measures makes it difficult to estimate the cost of energy-saving and carbon-reducing buildings in the early stages of project construction, which will have a serious impact on subsequent decision-making and management of the project. Therefore, it is crucial to conduct cost forecasts for energy-saving and carbon-reducing buildings in the early stages of project construction. Summary of the invention

[0004] The purpose of this application is to provide a cost prediction method, device, equipment, medium and product for energy-saving and carbon-reducing buildings.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting the cost of energy-saving and carbon-reducing buildings, comprising:

[0007] Acquire a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: conventional characteristic indicators of construction projects, the first characteristic data includes: conventional characteristic data of construction projects, the second characteristic indicator includes: energy-saving and carbon-reducing building incremental cost characteristic indicators, and the second characteristic data includes: energy-saving and carbon-reducing building incremental cost characteristic data;

[0008] Inputting the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building;

[0009] Inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings;

[0010] Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

[0011] In a second aspect, the present application provides a cost prediction device for energy-saving and carbon-reducing buildings, comprising:

[0012] An acquisition module is used to acquire a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: a conventional characteristic indicator of a construction project, the first characteristic data includes: conventional characteristic data of a construction project, the second characteristic indicator includes: an incremental cost characteristic indicator of an energy-saving and carbon-reducing building, and the second characteristic data includes: incremental cost characteristic data of an energy-saving and carbon-reducing building;

[0013] A prediction module, used for inputting the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building;

[0014] Inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings;

[0015] Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

[0016] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-mentioned methods for predicting the cost of energy-saving and carbon-reducing buildings.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting the cost of energy-saving and carbon-reducing buildings.

[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting the cost of energy-saving and carbon-reducing buildings.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] The present application provides a cost prediction method, device, equipment, medium and product for energy-saving and carbon-reducing buildings. Through fine feature screening and the learning ability of the SVR model, it ensures that the prediction results are highly consistent with the actual situation, providing a reliable cost reference for project decision makers, and the automation of the prediction process greatly improves decision-making efficiency, reduces manual intervention and data processing time, and enables the project team to respond quickly to market changes and make timely and wise investment decisions. It can also flexibly support the needs of customized design, allowing the project team to input corresponding feature indicators according to different design schemes, and instantly obtain the corresponding cost forecast, providing an economic feasibility analysis for innovative design. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of a cost prediction method for energy-saving and carbon-reducing buildings provided in one embodiment of the present application;

[0023] Figure 2 One of the flowcharts of a method for training an energy-saving and carbon-reducing building incremental cost prediction model provided in one embodiment of the present application;

[0024] Figure 3 A logical schematic diagram of a method for training an energy-saving and carbon-reducing building incremental cost prediction model provided in one embodiment of the present application;

[0025] Figure 4 A second flow chart of a method for training an energy-saving and carbon-reducing building incremental cost prediction model provided in an embodiment of the present application;

[0026] Figure 5 A flowchart of a method for training a total cost prediction model for energy-saving and carbon-reducing buildings provided in one embodiment of the present application;

[0027] Figure 6 A logical schematic diagram of a method for training a total cost prediction model for energy-saving and carbon-reducing buildings provided in one embodiment of the present application;

[0028] Figure 7 A schematic diagram of functional modules of a cost prediction device for energy-saving and carbon-reducing buildings provided in one embodiment of the present application;

[0029] Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] like Figure 1 As shown, some embodiments of the present application provide a method for predicting the cost of energy-saving and carbon-reducing buildings. In the embodiments of the present application, the following steps 101 to 103 are included. Among them:

[0032] Step 101, obtaining a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: conventional characteristic indicators of construction projects, the first characteristic data includes: conventional characteristic data of construction projects, the second characteristic indicator includes: energy-saving and carbon-reducing building incremental cost characteristic indicators, and the second characteristic data includes: energy-saving and carbon-reducing building incremental cost characteristic data;

[0033] In the embodiment of the present application, the conventional characteristic indicators of the construction project generally include the basic attributes of the building, such as building area, building height, number of floors, structure type, service life, etc. These indicators reflect the general characteristics and basic conditions of the building and are the basis for the construction cost prediction.

[0034] The incremental cost characteristic index of energy-saving and carbon-reducing buildings refers to the incremental cost caused by the adoption of energy-saving and carbon-reducing technologies. For example, the improvement of the heat transfer coefficient of the exterior wall, the installation of solar photovoltaic systems, the purchase of high-efficiency energy-saving equipment, etc. These incremental costs are important characteristics that distinguish energy-saving and carbon-reducing buildings from traditional buildings, and are also factors that need to be specially considered when predicting the total construction cost.

[0035] The data source can be the internal database of the cost enterprise, the engineering cost information network, the cost database system and other public databases. At the same time, relevant standards and policy documents can also be referred to to ensure the accuracy and authority of the data.

[0036] Step 102, inputting the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building;

[0037] In the embodiment of the present application, the collected conventional characteristic indicators of the construction project (including but not limited to functional formats, building area, number of building floors, building height, structure type, assembly rate, number of podium floors, podium area, facade decoration category, roof type, window-to-wall ratio, shape coefficient, volume ratio, C30 concrete unit price, three-grade steel unit price and green building star rating, etc.), and energy-saving and carbon-reducing building incremental cost characteristic indicators (including but not limited to roof heat transfer coefficient improvement ratio, exterior wall heat transfer coefficient improvement ratio, door and window heat transfer coefficient improvement ratio, facade material durability, building sound insulation structure, air conditioning cold and heat source energy efficiency improvement, rainwater recycling system, use of BIM technology, etc.), the conventional characteristic data of the construction project corresponding to the conventional characteristic indicators of the construction project and the energy-saving and carbon-reducing building incremental cost characteristic data corresponding to the energy-saving and carbon-reducing building incremental cost characteristic indicators are used as input data. These characteristic indicators comprehensively and meticulously reflect the characteristics of the construction project and the energy-saving and carbon-reducing technical measures adopted.

[0038] The incremental cost prediction model for energy-saving and carbon-reducing buildings uses the SVR algorithm to deeply learn the patterns and rules contained in the historical data set based on the input feature indicator data. During the model learning process, the model will comprehensively consider the impact of various feature indicators on the incremental cost of energy-saving and carbon-reducing buildings. After training, the model can predict the incremental cost of the energy-saving and carbon-reducing building, that is, the additional costs incurred due to the use of specific energy-saving and carbon-reducing technologies. This part of the cost information is of great significance for the early decision-making, budget formulation and subsequent cost control of the project.

[0039] The energy-saving and carbon-reducing building incremental cost prediction model outputs the energy-saving and carbon-reducing building incremental cost prediction data, which includes not only specific cost values, but also a detailed analysis of the cost composition, helping project managers to more clearly understand which energy-saving and carbon-reducing technologies have led to cost increases and the extent of the increase. This helps them make more reasonable choices and adjustments during the project planning and design stages.

[0040] Step 103, inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings;

[0041] In an embodiment of the present application, the conventional characteristic data of the construction project and the predicted incremental cost data predicted in the previous step are used as input data of the total cost prediction model of energy-saving and carbon-reducing buildings. In the learning process of the total cost prediction model of energy-saving and carbon-reducing buildings, it will not only consider the basic impact of the conventional characteristic indicators of the construction project on the total cost, but also take the predicted incremental cost data of energy-saving and carbon-reducing buildings into consideration, and comprehensively evaluate the comprehensive effect of all factors on the total cost. After training, the model can predict the total cost of the energy-saving and carbon-reducing building. The total cost information of the energy-saving and carbon-reducing building output by the model is a comprehensive and accurate cost estimate. This total cost includes both the traditional building cost part, that is, the basic construction cost without adopting any energy-saving and carbon-reducing technology; it also includes the incremental cost generated by the adoption of a series of energy-saving and carbon-reducing technologies. Such total cost information provides project managers with a clear and complete cost view, which helps them make more scientific and reasonable arrangements in project decision-making, fund raising, cost control, etc.

[0042] Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

[0043] In the embodiments of the present application, the SVR algorithm (Support Vector Regression) is a machine learning method based on statistical learning theory, which is particularly suitable for processing small sample, nonlinear and high-dimensional space data. The SVR algorithm minimizes the prediction error by finding an optimal hyperplane, thereby achieving accurate prediction of unknown data. In this case, the incremental cost prediction model for energy-saving and carbon-reducing buildings and the total cost prediction model for energy-saving and carbon-reducing buildings are both machine learning models built based on the SVR algorithm. These models can automatically extract patterns from the data and make accurate predictions on new data by learning the relationship between feature indicators and costs from historical data.

[0044] The embodiment of the present application ensures that the prediction results are highly consistent with the actual situation through fine feature screening and the learning ability of the SVR model, providing a reliable cost reference for project decision makers, and the automation of the prediction process greatly improves the decision-making efficiency, reduces manual intervention and data processing time, and enables the project team to respond quickly to market changes and make timely and wise investment decisions. It can also flexibly support the needs of customized design, allowing the project team to input corresponding feature indicators according to different design schemes and instantly obtain corresponding cost forecasts, providing economic feasibility analysis for innovative designs.

[0045] Optionally, refer to Figure 2 The energy-saving and carbon-reducing building incremental cost prediction model is trained by the following steps:

[0046] Step 201, obtaining the first sample characteristic index and first sample characteristic data, the second sample characteristic index and the second sample characteristic data of the completed energy-saving and carbon-reducing buildings, wherein the first sample characteristic index includes: conventional characteristic index of sample construction projects, the first sample characteristic data includes: conventional characteristic data of sample construction projects and sample cost data, the second sample characteristic index includes: incremental cost characteristic index of sample energy-saving and carbon-reducing buildings, and the second sample characteristic data includes: incremental cost characteristic data of sample energy-saving and carbon-reducing buildings and historical incremental cost data;

[0047] Step 202, constructing a second feature index library and a second feature database based on the second sample feature index and the second sample feature data;

[0048] Step 203, constructing a first feature index library and a first feature database based on the first sample feature data and the first sample feature index;

[0049] Step 204: Use the first feature database and the second feature database to train the initialized energy-saving and carbon-reducing building incremental cost prediction model.

[0050] In the embodiment of the present application, the collected first sample characteristic index and first sample characteristic data, second sample characteristic index and second sample characteristic data are sorted, classified and encoded to form a standardized characteristic index library, which is helpful for subsequent data analysis and model training.

[0051] The historical incremental cost data and the second sample feature data are combined to construct the second sample feature database, which contains not only the conventional factors affecting the construction cost, but also the incremental cost factors of energy-saving and carbon-reduction technologies.

[0052] The initialized energy-saving and carbon-reducing building incremental cost prediction model is trained using the constructed second sample feature database and the first sample feature database.

[0053] During the training process, the model will learn the relationship between feature indicators and construction costs, and optimize the prediction performance by continuously adjusting model parameters.

[0054] Once training is complete, the model will be able to quickly and accurately predict the incremental cost of a project based on the input energy-saving and carbon-reduction building characteristic indicators.

[0055] Specifically, refer to Figure 3 The SVR algorithm refers to an energy-saving and carbon-reducing building incremental cost prediction algorithm established by the support vector machine regression method.

[0056] Grid search and cross validation are processes set up to find the optimal parameter penalty factor c and kernel parameter g in the incremental cost prediction model of energy-saving and carbon-reducing buildings built based on the SVR algorithm. Specifically, the initial value of c is set to 1, and the initial value of g is set to the inverse of the number of characteristic indicators, such as 0.0625, 0.07, etc., which can be set according to actual needs and are not limited here. A set of grids of parameters c and g are generated by the meshgrid function. For the randomly selected training set, the libsvmtrain and libsvmpredict functions are called at each parameter grid point to train and evaluate the incremental cost prediction model for energy-saving and carbon-reducing buildings, and cross-validate, and update the optimal parameter combination according to the results of cross-validation.

[0057] The embodiment of the present application can construct an incremental cost prediction model suitable for energy-saving and carbon-reducing buildings, providing a scientific basis for project decision makers. The model helps to improve the economic and social benefits of energy-saving and carbon-reducing building projects and promote the sustainable development of the construction industry.

[0058] Optionally, refer to Figure 4 , the step 204 comprises:

[0059] Step 2041, normalizing the data in the first sample feature database and the second sample feature database;

[0060] In the embodiment of the present application, normalization is a data preprocessing technique, the purpose of which is to convert data of different dimensions or ranges into the same dimension or range. In the incremental cost database, data may come from different projects or periods, with different numerical ranges and units. Normalization can ensure that the model treats all features equally during the training process, avoiding deviations caused by large differences in data ranges. Commonly used normalization methods include minimum-maximum normalization and Z-score normalization.

[0061] Step 2042, constructing an initialized energy-saving and carbon-reducing building incremental cost prediction model based on the SVR algorithm;

[0062] In the embodiment of the present application, SVR (Support Vector Regression) is a machine learning algorithm for regression analysis, which is based on the theoretical framework of support vector machine (SVM). The goal of SVR is to find a function that can predict the target value as accurately as possible while keeping the prediction error within a certain range. In this step, the SVR algorithm is used to initialize a prediction model that will be used to predict the incremental cost of energy-saving and carbon-reducing buildings.

[0063] Step 2043, using the first sample feature database and the second sample feature database to train the initialized energy-saving and carbon-reducing building incremental cost prediction model;

[0064] In the embodiment of the present application, the incremental cost prediction model for energy-saving and carbon-reducing buildings will be trained using part of the data in the second sample database consisting of historical incremental cost data and second sample feature data and the first sample database. These training data contain various feature indicators and corresponding cost data related to the incremental cost of energy-saving and carbon-reducing buildings. Through training, the model will learn how to predict incremental costs based on the input feature indicators.

[0065] Step 2044, when the trained energy-saving and carbon-reducing building incremental cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reducing building incremental cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reducing building incremental cost prediction model meets the training requirements.

[0066] In the embodiment of the present application, after the model training is completed, it is necessary to evaluate whether its performance meets the predetermined training requirements (such as prediction accuracy, generalization ability, etc.). If it does not meet the requirements, parameter adjustment is required to optimize the model performance.

[0067] Grid search is an exhaustive search method used to systematically traverse multiple parameter combinations to determine the optimal parameter settings. In this step, grid search will be used to adjust the parameters of the SVR model (such as penalty parameter C, kernel function parameters, etc.) to improve the predictive performance of the model.

[0068] Cross-validation is a method for evaluating model performance. It divides the dataset into multiple parts, uses one part as the test set and the rest as the training set in turn to evaluate the performance of the model on different datasets. Through cross-validation, the generalization ability of the model can be evaluated more accurately and overfitting can be avoided.

[0069] If the performance of the model still does not meet the requirements after parameter adjustment and cross-validation, you need to repeat the above process until you find the model parameter settings that meet the training requirements.

[0070] Optionally, refer to Figure 5 The total cost prediction model for energy-saving and carbon-reducing buildings is trained by the following steps:

[0071] Step 301, adding the predicted incremental cost data output by the trained energy-saving and carbon-reducing building incremental cost prediction model to the first sample feature database;

[0072] Step 302, normalizing the supplemented first sample feature database;

[0073] Step 303, constructing an initialized energy-saving and carbon-reducing building total cost prediction model based on the SVR algorithm;

[0074] Step 304, using the supplemented first sample feature database to train the initialized energy-saving and carbon-reducing building total cost prediction model;

[0075] Step 305, when the trained energy-saving and carbon-reducing building total cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reducing building total cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reducing building total cost prediction model meets the training requirements.

[0076] In the embodiment of the present application, the normalization method of the supplemented first sample feature database can refer to the normalization method described in step 2041, which will not be repeated here.

[0077] After the total cost prediction model for energy-saving and carbon-reducing buildings is initialized, it needs to be trained with actual data so that it can learn the patterns and rules in the data. The first sample feature index library corresponding to the supplemented first sample feature database can include multiple aspects such as building area, building material cost, energy efficiency level, geographical location, etc., and the supplemented first sample feature database also contains the predicted incremental cost data output by the energy-saving and carbon-reducing building incremental cost prediction model. The researchers will use these data to train the initialized model so that the model can predict the corresponding total building cost based on the database corresponding to the input feature index.

[0078] After training is completed, the performance of the model needs to be evaluated to determine whether it meets the predetermined training requirements. These requirements may include prediction accuracy, stability, generalization ability, etc. If the model after training does not achieve the expected effect, the model performance can be improved by further optimizing the model.

[0079] If the performance of the model still does not meet the requirements after one parameter adjustment and cross-validation, it is necessary to repeat this process, continuously adjust the parameters and perform cross-validation until a set of parameter settings is found that makes the model meet the training requirements.

[0080] Reference Figure 6 The energy-saving and carbon-reducing building cost is based on the energy-saving and carbon-reducing building total cost characteristic index library as input data, and the energy-saving and carbon-reducing building cost is used as the prediction target to establish the energy-saving and carbon-reducing building cost prediction model.

[0081] Optionally, the second characteristic index includes: the improvement ratio of roof heat transfer coefficient, the improvement ratio of exterior wall heat transfer coefficient, the improvement ratio of door and window heat transfer coefficient, the proportion of sunshade facilities to exterior window transparency, the durability of facade materials, building sound insulation structure, anti-slip paving, waste-recycling building materials, shock absorption measures, the proportion of high-strength concrete, the proportion of high-strength steel, air-conditioning cold and heat source energy efficiency improvement, heating boiler energy efficiency improvement, room conditioner / split air-conditioning energy efficiency improvement, setting up air quality monitoring and display system, setting up underground garage CO concentration monitoring, durability of pipes and fittings, setting up rainwater recycling system, setting up water remote metering system, water efficiency of water-saving appliances, setting up energy-saving lighting, setting up safety lighting, setting up intelligent lighting control system, setting up daylight sensing lighting system, independent sub-item measurement of cables and energy consumption, use of energy-saving elevators, energy efficiency rating of three-phase distribution transformers, energy efficiency rating of fans and water pumps, durability of waterproof and sealing materials, durability of interior decoration materials, setting up solar photovoltaic system, solar water heating system, setting up ground source heat pump system, using green building materials, using at least one of BIM technology.

[0082] In an embodiment of the present application, the second characteristic indicator library can be established by screening the incremental cost characteristic indicators of energy-saving and carbon-reducing buildings through strong exclusion, conventional standard exclusion, expert scoring method, and correlation coefficient.

[0083] Exemplarily, the second feature index library may be as shown in Table 1 below:

[0084] Table 1

[0085]

[0086]

[0087]

[0088] Among them, the improvement of the roof heat transfer coefficient is used to describe the improvement of the roof insulation performance, and the thermal performance is improved in accordance with the "General Specification for Energy Conservation and Renewable Energy Utilization in Buildings" (GB55015-2021).

[0089] The improvement in the exterior wall heat transfer coefficient is used to describe the improvement in the exterior wall insulation performance, and the thermal performance is improved in accordance with the "General Specification for Energy Conservation and Renewable Energy Utilization in Buildings" (GB55015-2021).

[0090] The improvement in the heat transfer coefficient of doors and windows is used to describe the improvement in the thermal insulation performance of doors and windows, and the thermal performance is improved in accordance with the "General Specification for Energy Conservation and Renewable Energy Utilization in Buildings" (GB55015-2021).

[0091] The durability of facade materials is used to describe that the exterior finishing materials are made of water-based fluorine coatings or coatings with equivalent weather resistance, and the weather resistance meets the requirements for superior products in the current national standard "Water-based Fluorine Coatings for Construction" HG / T 4104-2009.

[0092] Building sound insulation structure is used to describe the building sound insulation design that meets GB55016 General Standard for Building Environment.

[0093] Anti-slip paving is used to describe the anti-slip performance of paving materials that meets the requirements of product standards.

[0094] The energy efficiency improvement of air conditioning cold and heat sources is used to describe 1. Multi-split (heat pump) air-conditioning units: the comprehensive refrigeration performance coefficient (IPLV) is improved by 8% or 16% compared with the current Shanghai "Public Building Energy Saving Design Standard" DGJ08-107 requirements. 2. Chillers: The refrigeration performance coefficient (COP) is improved by 6% or 12% compared with the current Shanghai "Public Building Energy Saving Design Standard" DGJ08-107 requirements.

[0095] Setting up a rainwater reuse system is used to describe the setting up of a rainwater collection and reuse system.

[0096] Setting up a remote water metering system is used to describe the setting up of remote water meters, classified and graded recording, and statistical analysis.

[0097] The water efficiency of water-saving appliances is used to describe the water efficiency level of sanitary appliances reaching level 1.

[0098] Setting up an intelligent lighting control system is used to describe 1. Zoning and grouping control based on building usage and natural lighting conditions; 2. The lighting of public places such as corridors, stairwells, foyers, toilets, parking garages, etc. should be controlled by centralized switches or on-site sensing; 3. Intelligent lighting control systems should be used for lighting in large spaces, multi-functions, and multi-scene places.

[0099] The energy efficiency grade of three-phase distribution transformer is used to describe the compliance with the Level 2 requirements or Level 1 requirements of the current national standard "Energy Efficiency Limit Values ​​and Energy Saving Evaluation Values ​​of Three-Phase Distribution Transformers" GB20052.

[0100] The fan and water pump energy efficiency grade is used to describe the secondary energy efficiency requirements of water pumps and fans that use frequency conversion technology to meet the corresponding energy efficiency evaluation standards.

[0101] The durability of waterproofing and sealing materials is used to describe the selected materials whose durability complies with the requirements of GB / T35608-2017 "Green Product Evaluation of Waterproofing and Sealing Materials".

[0102] The durability of interior decoration and finishing materials is used to describe whether the durability of decoration and finishing materials meets the requirements of corresponding product standards.

[0103] Setting up a solar photovoltaic system is used to describe the setting and complies with the provisions of the current Shanghai Standard "Residential Design Standard" DGJ08-20, Shanghai Standard "Public Building Energy Saving Design Standard" DGJ08-107 and "Residential Building Energy Saving Design Standard" DGJ08-205.

[0104] Setting up a solar water heating system is used to describe the setting and complies with the relevant provisions of the current Shanghai Standard "Technical Code for Solar Water Heating Systems" DG / T08-2004A.

[0105] The use of BIM technology is used to describe the application of BIM technology in the design stage and construction stage.

[0106] Optionally, the first characteristic indicator includes: functional business type, building area, number of building floors, building height, seismic resistance level, foundation type, structure type, proportion of high-strength steel bars, assembly rate, number of podium floors, podium area, podium structure type, masonry type, interior decoration category, facade decoration category, door and window type, roof type, window-to-wall ratio, shape coefficient, volume ratio, greening rate, service life, C30 concrete information price during the construction period, and at least one of the third-grade steel bar information price during the construction period.

[0107] In an embodiment of the present application, the construction of the energy-saving and carbon-reducing building total cost characteristic index library is to screen the conventional characteristic indicators of construction projects. The specific screening method is the expert scoring method and the correlation coefficient ranking method. The above-screened energy-saving and carbon-reducing building total cost characteristic indicators and the incremental cost together constitute the energy-saving and carbon-reducing building total cost characteristic index library.

[0108] For example, the conventional characteristic indicators of construction projects can be as shown in Table 2:

[0109] Table 2

[0110]

[0111] Based on the same inventive concept, the embodiment of the present application also provides a cost prediction device for energy-saving and carbon-reducing buildings for implementing the cost prediction method for energy-saving and carbon-reducing buildings involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the cost prediction device for energy-saving and carbon-reducing buildings provided below can refer to the limitations of the cost prediction method for energy-saving and carbon-reducing buildings above, and will not be repeated here.

[0112] In an exemplary embodiment, Figure 7 As shown, a cost prediction device 40 for energy-saving and carbon-reducing buildings is provided, comprising:

[0113] The acquisition module 401 is used to acquire a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: a conventional characteristic indicator of a construction project, the first characteristic data includes: conventional characteristic data of a construction project, the second characteristic indicator includes: an incremental cost characteristic indicator of an energy-saving and carbon-reducing building, and the second characteristic data includes: incremental cost characteristic data of an energy-saving and carbon-reducing building, and historical incremental cost data;

[0114] A prediction module 402 is used to input the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building;

[0115] Inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings;

[0116] Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

[0117] Optionally, the prediction module 402 is further configured to:

[0118] Obtaining first sample characteristic indicators and first sample characteristic data, second sample characteristic indicators and second sample characteristic data of completed energy-saving and carbon-reducing buildings, wherein the first sample characteristic indicators include: conventional characteristic indicators of sample construction projects, the first sample characteristic data include: conventional characteristic data of sample construction projects and sample cost data, the second sample characteristic indicators include: incremental cost characteristic indicators of sample energy-saving and carbon-reducing buildings, and the second sample characteristic data include: incremental cost characteristic data of sample energy-saving and carbon-reducing buildings and historical incremental cost data;

[0119] Building a second feature index library and a second feature database based on the second sample feature index and the second sample feature data;

[0120] Building a first feature index library and a first feature database based on the first sample feature data and the first sample feature index;

[0121] The first feature database and the second feature database are used to train the initialized energy-saving and carbon-reducing building incremental cost prediction model.

[0122] Optionally, the prediction module 402 is further configured to:

[0123] Normalizing the data in the first sample feature database and the second sample feature database;

[0124] An initialization model for predicting the incremental cost of energy-saving and carbon-reducing buildings is constructed based on the SVR algorithm;

[0125] Using the first sample feature database and the second sample feature database to train the initialized energy-saving and carbon-reducing building incremental cost prediction model;

[0126] When the trained energy-saving and carbon-reduction building incremental cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reduction building incremental cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reduction building incremental cost prediction model meets the training requirements.

[0127] Optionally, the prediction module 402 is further configured to:

[0128] Normalizing the supplemented first sample feature database;

[0129] Based on the SVR algorithm, an initial total cost prediction model for energy-saving and carbon-reducing buildings is constructed;

[0130] Using the supplemented first sample feature database to train the initialized energy-saving and carbon-reducing building total cost prediction model;

[0131] When the trained energy-saving and carbon-reducing building total cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reducing building total cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reducing building total cost prediction model meets the training requirements.

[0132] Optionally, the first characteristic indicator includes: functional business type, building area, number of building floors, building height, seismic resistance level, foundation type, structure type, proportion of high-strength steel bars, assembly rate, number of podium floors, podium area, podium structure type, masonry type, interior decoration category, facade decoration category, door and window type, roof type, window-to-wall ratio, shape coefficient, volume ratio, greening rate, service life, C30 concrete information price during the construction period, and at least one of the third-grade steel bar information price during the construction period.

[0133] Optionally, the second characteristic index includes: the improvement ratio of roof heat transfer coefficient, the improvement ratio of exterior wall heat transfer coefficient, the improvement ratio of door and window heat transfer coefficient, the proportion of sunshade facilities to exterior window transparency, the durability of facade materials, building sound insulation structure, anti-slip paving, waste-recycling building materials, shock absorption measures, the proportion of high-strength concrete, the proportion of high-strength steel, air-conditioning cold and heat source energy efficiency improvement, heating boiler energy efficiency improvement, room conditioner / split air-conditioning energy efficiency improvement, setting up air quality monitoring and display system, setting up underground garage CO concentration monitoring, durability of pipes and fittings, setting up rainwater recycling system, setting up water remote metering system, water efficiency of water-saving appliances, setting up energy-saving lighting, setting up safety lighting, setting up intelligent lighting control system, setting up daylight sensing lighting system, independent sub-item measurement of cables and energy consumption, use of energy-saving elevators, energy efficiency rating of three-phase distribution transformers, energy efficiency rating of fans and water pumps, durability of waterproof and sealing materials, durability of interior decoration materials, setting up solar photovoltaic system, solar water heating system, setting up ground source heat pump system, using green building materials, using at least one of BIM technology.

[0134] The embodiment of the present application ensures that the prediction results are highly consistent with the actual situation through fine feature screening and the learning ability of the SVR model, providing a reliable cost reference for project decision makers, and the automation of the prediction process greatly improves the decision-making efficiency, reduces manual intervention and data processing time, and enables the project team to respond quickly to market changes and make timely and wise investment decisions. It can also flexibly support the needs of customized design, allowing the project team to input corresponding feature indicators according to different design schemes and instantly obtain corresponding cost forecasts, providing economic feasibility analysis for innovative designs.

[0135] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store cost prediction data of energy-saving and carbon-reducing buildings. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a cost prediction method for energy-saving and carbon-reducing buildings is implemented.

[0136] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0138] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0139] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0141] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0142] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0143] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for predicting the cost of energy-saving and carbon-reducing buildings, characterized in that: The cost prediction method of the energy-saving and carbon-reducing building includes: Acquire a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: conventional characteristic indicators of construction projects, the first characteristic data includes: conventional characteristic data of construction projects, the second characteristic indicator includes: energy-saving and carbon-reducing building incremental cost characteristic indicators, and the second characteristic data includes: energy-saving and carbon-reducing building incremental cost characteristic data; Inputting the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building; Inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings; Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

2. The cost prediction method for energy-saving and carbon-reducing buildings according to claim 1 is characterized in that: The energy-saving and carbon-reducing building incremental cost prediction model is trained by the following steps: Obtaining first sample characteristic indicators and first sample characteristic data, second sample characteristic indicators and second sample characteristic data of completed energy-saving and carbon-reducing buildings, wherein the first sample characteristic indicators include: conventional characteristic indicators of sample construction projects, the first sample characteristic data include: conventional characteristic data of sample construction projects and sample cost data, the second sample characteristic indicators include: incremental cost characteristic indicators of sample energy-saving and carbon-reducing buildings, and the second sample characteristic data include: incremental cost characteristic data of sample energy-saving and carbon-reducing buildings and historical incremental cost data; Building a second feature index library and a second feature database based on the second sample feature index and the second sample feature data; Building a first feature index library and a first feature database based on the first sample feature data and the first sample feature index; The first feature database and the second feature database are used to train the initialized energy-saving and carbon-reducing building incremental cost prediction model.

3. The cost prediction method for energy-saving and carbon-reducing buildings according to claim 2 is characterized in that: The step of using the first feature database and the second feature database to train the initialized energy-saving and carbon-reducing building incremental cost prediction model includes: Normalizing the data in the first sample feature database and the second sample feature database; An initialization model for predicting the incremental cost of energy-saving and carbon-reducing buildings is constructed based on the SVR algorithm; Using the first sample feature database and the second sample feature database to train the initialized energy-saving and carbon-reducing building incremental cost prediction model; When the trained energy-saving and carbon-reduction building incremental cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reduction building incremental cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reduction building incremental cost prediction model meets the training requirements.

4. The cost prediction method for energy-saving and carbon-reducing buildings according to claim 2 is characterized in that: The total cost prediction model for energy-saving and carbon-reducing buildings is trained by the following steps: Supplementing the predicted incremental cost data output by the trained energy-saving and carbon-reducing building incremental cost prediction model into the first sample feature database; Normalizing the supplemented first sample feature database; Based on the SVR algorithm, an initial total cost prediction model for energy-saving and carbon-reducing buildings is constructed; Using the supplemented first sample feature database to train the initialized energy-saving and carbon-reducing building total cost prediction model; When the trained energy-saving and carbon-reducing building total cost prediction model does not meet the training requirements, the parameters of the energy-saving and carbon-reducing building total cost prediction model are adjusted through grid search and then cross-validated until the trained energy-saving and carbon-reducing building total cost prediction model meets the training requirements.

5. The cost prediction method for energy-saving and carbon-reducing buildings according to claim 1 is characterized in that: The first characteristic indicators include: functional business, building area, number of building floors, building height, seismic resistance level, foundation type, structure type, proportion of high-strength steel bars, assembly rate, number of podium floors, podium area, podium structure type, masonry type, interior decoration category, facade decoration category, door and window type, roof type, window-to-wall ratio, shape coefficient, volume ratio, greening rate, service life, C30 concrete information price during the construction period, and grade 3 steel bar information price during the construction period.

6. The cost prediction method for energy-saving and carbon-reducing buildings according to claim 1 is characterized in that: The second characteristic indicators include: the improvement ratio of roof heat transfer coefficient, the improvement ratio of exterior wall heat transfer coefficient, the improvement ratio of door and window heat transfer coefficient, the ratio of sunshade facilities to exterior window transparency, the durability of facade materials, building sound insulation structure, anti-slip paving, waste-recycling building materials, shock absorption measures, the proportion of high-strength concrete, the proportion of high-strength steel, air conditioning cold and heat source energy efficiency improvement, heating boiler energy efficiency improvement, room conditioner / split air conditioner energy efficiency improvement, setting up air quality monitoring and display system, setting up underground garage CO concentration monitoring, durability of pipes and fittings, setting up rainwater recycling system, setting up water remote metering system, water efficiency of water-saving appliances, setting up energy-saving lighting, setting up safety lighting, setting up intelligent lighting control system, setting up daylight sensing lighting system, independent sub-item measurement of cables and energy consumption, use of energy-saving elevators, energy efficiency rating of three-phase distribution transformers, energy efficiency rating of fans and water pumps, durability of waterproof and sealing materials, durability of interior decoration materials, setting up solar photovoltaic system, solar water heating system, setting up ground source heat pump system, using green building materials, and using at least one of BIM technology.

7. A cost prediction device for energy-saving and carbon-reducing buildings, characterized in that: The cost prediction device for energy-saving and carbon-reducing buildings comprises: An acquisition module is used to acquire a first characteristic indicator and first characteristic data, a second characteristic indicator and a second characteristic data, wherein the first characteristic indicator includes: a conventional characteristic indicator of a construction project, the first characteristic data includes: conventional characteristic data of a construction project, the second characteristic indicator includes: an incremental cost characteristic indicator of an energy-saving and carbon-reducing building, and the second characteristic data includes: incremental cost characteristic data of an energy-saving and carbon-reducing building; A prediction module, used for inputting the first characteristic data and the second characteristic data into an energy-saving and carbon-reducing building incremental cost prediction model to obtain the predicted incremental cost data of the energy-saving and carbon-reducing building; Inputting the first characteristic data and the predicted incremental cost data into a total cost prediction model for energy-saving and carbon-reducing buildings to obtain total cost information for the energy-saving and carbon-reducing buildings; Among them, the energy-saving and carbon-reducing building incremental cost prediction model and the energy-saving and carbon-reducing building total cost prediction model are machine learning models constructed based on the SVR algorithm.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting the cost of energy-saving and carbon-reducing buildings described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the construction cost of energy-saving and carbon-reducing buildings described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for predicting the cost of energy-saving and carbon-reducing buildings described in any one of claims 1 to 6 are implemented.

Images